Client Report - Can You Predict That?

Table of contents

• Elevator pitch
• QUESTION|TASK 1
• QUESTION|TASK 2
• QUESTION|TASK 3
• QUESTION|TASK 4
• STRETCH QUESTION|TASK 1
• STRETCH QUESTION|TASK 2
• STRETCH QUESTION|TASK 3

!pip install tensorflow
import pandas as pd 
import numpy as np
from lets_plot import *
import matplotlib.pyplot as plt
import xgboost as xgb
from xgboost import XGBClassifier, XGBRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix
import matplotlib.pyplot as plt
from sklearn.metrics import classification_report
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense
from sklearn.model_selection import train_test_split
from sklearn.metrics import root_mean_squared_error, r2_score
from sklearn.preprocessing import MinMaxScaler

LetsPlot.setup_html(isolated_frame=True)

Requirement already satisfied: tensorflow in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (2.18.0)
Requirement already satisfied: tensorflow-intel==2.18.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow) (2.18.0)
Requirement already satisfied: absl-py>=1.0.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (2.1.0)
Requirement already satisfied: astunparse>=1.6.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (1.6.3)
Requirement already satisfied: flatbuffers>=24.3.25 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (25.2.10)
Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (0.6.0)
Requirement already satisfied: google-pasta>=0.1.1 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (0.2.0)
Requirement already satisfied: libclang>=13.0.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (18.1.1)
Requirement already satisfied: opt-einsum>=2.3.2 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (3.4.0)
Requirement already satisfied: packaging in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (23.2)
Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<6.0.0dev,>=3.20.3 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (5.29.3)
Requirement already satisfied: requests<3,>=2.21.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (2.31.0)
Requirement already satisfied: setuptools in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (75.8.0)
Requirement already satisfied: six>=1.12.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (1.16.0)
Requirement already satisfied: termcolor>=1.1.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (2.5.0)
Requirement already satisfied: typing-extensions>=3.6.6 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (4.12.2)
Requirement already satisfied: wrapt>=1.11.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (1.17.2)
Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (1.70.0)
Requirement already satisfied: tensorboard<2.19,>=2.18 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (2.18.0)
Requirement already satisfied: keras>=3.5.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (3.9.0)
Requirement already satisfied: numpy<2.1.0,>=1.26.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (1.26.3)
Requirement already satisfied: h5py>=3.11.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (3.13.0)
Requirement already satisfied: ml-dtypes<0.5.0,>=0.4.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorflow-intel==2.18.0->tensorflow) (0.4.1)
Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.18.0->tensorflow) (0.45.1)
Requirement already satisfied: rich in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from keras>=3.5.0->tensorflow-intel==2.18.0->tensorflow) (13.9.4)
Requirement already satisfied: namex in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from keras>=3.5.0->tensorflow-intel==2.18.0->tensorflow) (0.0.8)
Requirement already satisfied: optree in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from keras>=3.5.0->tensorflow-intel==2.18.0->tensorflow) (0.14.1)
Requirement already satisfied: charset-normalizer<4,>=2 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.18.0->tensorflow) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.18.0->tensorflow) (3.6)
Requirement already satisfied: urllib3<3,>=1.21.1 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.18.0->tensorflow) (2.1.0)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.18.0->tensorflow) (2023.11.17)
Requirement already satisfied: markdown>=2.6.8 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorboard<2.19,>=2.18->tensorflow-intel==2.18.0->tensorflow) (3.7)
Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorboard<2.19,>=2.18->tensorflow-intel==2.18.0->tensorflow) (0.7.2)
Requirement already satisfied: werkzeug>=1.0.1 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from tensorboard<2.19,>=2.18->tensorflow-intel==2.18.0->tensorflow) (3.1.3)
Requirement already satisfied: MarkupSafe>=2.1.1 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from werkzeug>=1.0.1->tensorboard<2.19,>=2.18->tensorflow-intel==2.18.0->tensorflow) (3.0.2)
Requirement already satisfied: markdown-it-py>=2.2.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from rich->keras>=3.5.0->tensorflow-intel==2.18.0->tensorflow) (3.0.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from rich->keras>=3.5.0->tensorflow-intel==2.18.0->tensorflow) (2.19.1)
Requirement already satisfied: mdurl~=0.1 in c:\users\jadab\appdata\local\programs\python\python312\lib\site-packages (from markdown-it-py>=2.2.0->rich->keras>=3.5.0->tensorflow-intel==2.18.0->tensorflow) (0.1.2)

Elevator pitch

A SHORT (2-3 SENTENCES) PARAGRAPH THAT DESCRIBES KEY INSIGHTS TAKEN FROM METRICS IN THE PROJECT RESULTS THINK TOP OR MOST IMPORTANT RESULTS. (Note: this is not a summary of the project, but a summary of the results.)

I was able to create a machine learning model that used features like if the home is one story and the quality of the building materials to decide whether the home was built before or after 1980 with an F1 score of about 0.94. When I added the additional features from the expanded dataset I got that F1 score up to about 0.97, so it did a lot better.

QUESTION|TASK 1

Create 2-3 charts that evaluate potential relationships between the home variables and before1980. Explain what you learn from the charts that could help a machine learning algorithm.

First, the vast majority of one-story homes were built since 1980. I did some research into why most one-story homes are of newer construction, and it seems to be because in the 1980’s and later is when the Baby Boomer generation started to need more accessible homes, and they didn’t need to be very large (as they were living mostly on their own or just as couples), so a lot more single-story homes were built to accommodate them, as their generation is massive proportionally.

df = pd.read_csv("https://raw.githubusercontent.com/byuidatascience/data4dwellings/master/data-raw/dwellings_ml/dwellings_ml.csv")

df_plotting = df.copy()
df_plotting['arcstyle_ONE-STORY'] = df_plotting['arcstyle_ONE-STORY'].astype('bool')
df_plotting['before1980'] = df_plotting['before1980'].astype('bool')

legend_labels = {
    'true': 'Before 1980',
    'false': 'Since 1980'
  }

(
  ggplot(df_plotting, aes(x="arcstyle_ONE-STORY",fill='before1980'))
  + geom_bar(stat='count', position='dodge')
  + scale_fill_manual(
      values = ['#e6272f', '#6d9ade'],
      name = "House Built:",
      labels = legend_labels
    )
  + labs(
      title="One Story Homes Before and After 1980",
      x="One Story",
      y='Number of Homes'
    )
  + theme(
      plot_title=element_text(size=20)
    )
)

Secondly, most homes without attached garages were built since 1980. I honestly cannot find anything about why this might be happening, but my guess would be that they are becoming less popular for aesthetic reasons.

df_plotting['gartype_Att'] = df_plotting['gartype_Att'].astype('bool')

(
  ggplot(df_plotting, aes(x="gartype_Att",fill='before1980'))
  + geom_bar(stat='count', position='dodge')
  + scale_fill_manual(
      values = ['#e6272f', '#6d9ade'],
      name = "House Built:",
      labels = legend_labels
    )
  + labs(
      title="Homes with Attached Garages Before and After 1980",
      x="Attached Garage",
      y='Number of Homes'
    )
  + theme(
      plot_title=element_text(size=20)
    )
)

Thirdly, the data has a “Quality” scale from A-D and X, which basically says how high quality the home is. The majority of the homes in the dataset are in the “C” category, meaning decent quality homes, but not the best. Most of the homes in this C category were built in or after 1980, which could suggest a lot more pre-built homes where the materials used weren’t decided by the homeowner. After 1980 it became a lot cheaper (hence the lower-quality building materials) and more popular to buy a home pre-built rather than build it yourself.

df_plotting['quality_C'] = df_plotting['quality_C'].astype('bool')

(
  ggplot(df_plotting, aes(x="quality_C",fill='before1980'))
  + geom_bar(stat='count', position='dodge')
  + scale_fill_manual(
      values = ['#e6272f', '#6d9ade'],
      name = "House Built:",
      labels = legend_labels
    )
  + labs(
      title='Homes of Quality "C" Before and After 1980',
      x="C-Quality",
      y='Number of Homes'
    )
  + theme(
      plot_title=element_text(size=20)
    )
)

QUESTION|TASK 2

Build a classification model labeling houses as being built “before 1980” or “during or after 1980”. Your goal is to reach or exceed 90% accuracy. Explain your final model choice (algorithm, tuning parameters, etc) and describe what other models you tried.

I went with an XGBClassifier model for this project because I am in the Machine Learning class right now and I remember my teacher in that class saying that XGBoost is often his go-to model if he needs to get things done quickly and well. For parameters I made the ‘objective’ ‘binary:hinge’, which basically tells it that the output should be either a 1 or a 0. The ‘eval_metric’ tells the model what to optimize, and the ‘error’ option is calculated as #(wrong cases)/#(all cases). I didn’t end up trying any other models because the XGBoost model got over 90% accuracy first try.

features_in_order_of_importance = ['livearea','basement','netprice','numbaths','smonth','finbsmnt','numbdrm','tasp','deduct','abstrprd','nocars','gartype_Att','sprice','quality_C','status_I','quality_D','condition_AVG','arcstyle_ONE-STORY','arcstyle_MIDDLE UNIT','stories','syear','qualified_Q','gartype_Det','arcstyle_ONE AND HALF-STORY','arcstyle_END UNIT','arcstyle_TWO-STORY','condition_Good','quality_B','quality_A','totunits','condition_VGood','arcstyle_TRI-LEVEL','quality_X','gartype_det/CP','arcstyle_BI-LEVEL','arcstyle_THREE-STORY','condition_Excel','arcstyle_TRI-LEVEL WITH BASEMENT','arcstyle_CONVERSIONS','gartype_CP','arcstyle_TWO AND HALF-STORY','gartype_Att/Det','qualified_U','gartype_None','arcstyle_SPLIT LEVEL','condition_Fair','gartype_att/CP','status_V']

X = df[features_in_order_of_importance]
y = df['before1980']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

model = XGBClassifier(
    objective='binary:hinge',
    eval_metric='error',
    use_label_encoder=False
)

model.fit(X_train, y_train)
y_pred = model.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred)
recall = recall_score(y_test, y_pred)
f1 = f1_score(y_test, y_pred)

print('Accuracy:', accuracy)
print('Precision:', precision)
print('Recall:', recall)
print('F1:', f1)

Accuracy: 0.9277765655684049
Precision: 0.9364697802197802
Recall: 0.9491820396797772
F1: 0.9427830596369923

QUESTION|TASK 3

Justify your classification model by discussing the most important features selected by your model. This discussion should include a feature importance chart and a description of the features.

I decided to do this part before part one, which is why I graphed the three most important features for that part. But as I already explained in part one, it makes sense that one story buildings would be the most important feature (because of the large population that is aging and needing single story homes). Basically I’m saying see task 1 for an explanation of the most important features.

influences = (pd.DataFrame({'importance': model.feature_importances_,
                           'feature': X_train.columns})
                           .sort_values('importance')
                           .query('importance >= 0.02'))

(
ggplot(data = influences, mapping = aes(x = 'feature', y = 'importance'))
  + geom_bar(stat = 'identity') 
  + coord_flip()
  + labs(
    x = "Feature",
    y = "Importance",
    title = "XGBoost Classifier Feature Importance"
  )
  + theme(plot_title=element_text(size=15,hjust=-4.1))

)

# importance_scores = model.feature_importances_
# feature_names = X_train.columns if hasattr(X_train, "columns") else np.arange(X_train.shape[1])
# sorted_indices = np.argsort(importance_scores)[::-1]

# for i in sorted_indices:
#     print(f"{feature_names[i]}: {importance_scores[i]}")

QUESTION|TASK 4

Describe the quality of your classification model using 2-3 different evaluation metrics. You also need to explain how to interpret each of the evaluation metrics you use.

You can see above (when I ran my model) what the accuracy, precision, recall, and f1 scores are for my model. Here is a quick explanation of each of these metrics:

Accuracy - The ratio of how many correct predictions to how many total predictions were made. This is not always the best metric because it does not tell us what the model is doing well on versus what it is failing on. What I mean is, if the data were 90% one category and 10% another category, the model could just predict the first category every time and have an accuracy score of 90%, which is decent. But the model would still not be very intelligent.

Precision - When a model makes a prediction of a certain category, what percent of the predictions for that category were correct? This is the precision. Having a high precision means the model had few “false positives”. But, focusing on just the precision score might induce a model to be very conservative in it’s “positive” predictions. It might decide to only guess a certain category if it is absolutely positive about it. That way the precision is very high.

Recall - Out of all the actual positives, how many did the model correctly identify? Focusing on recall can have the opposite effect as focusing on precision. Where precision makes the model more hesitant to guess “positive”, recall makes the model more likely to. Because if it guesses “positive” for all of them, the recall would be 100%.

F1 Score - F1 is a strange sort of balancing ratio between precision and recall that forces the model to focus on both rather than one or the other. A high F1 score means that the model performed well on both precision and recall. The F1 score is usually the most accurate to how your model is performing in general cases.

In this case, Recall might be the most useful thing to look for, because we would rather find all the houses with asbestos, even if we also include some that weren’t actually built before 1980. Better be safe and check all possible houses than only check a few of the houses and let some people go on living in homes with asbestos.

---

STRETCH QUESTION|TASK 1

Repeat the classification model using 3 different algorithms. Display their Feature Importance, and Decision Matrix. Explain the differences between the models and which one you would recommend to the Client.

type your results and analysis here

# DECISION TREE
from sklearn.tree import DecisionTreeClassifier

tree = DecisionTreeClassifier()
tree.fit(X_train, y_train)
tree_pred = tree.predict(X_test)

tree_accuracy = accuracy_score(y_test, tree_pred)
tree_precision = precision_score(y_test, tree_pred)
tree_recall = recall_score(y_test, tree_pred)
tree_f1 = f1_score(y_test, tree_pred)

print('Decision Tree')
print('Accuracy:', tree_accuracy)
print('Precision:', tree_precision)
print('Recall:', tree_recall)
print('F1:', tree_f1)
print('Confusion Matrix:')
print(confusion_matrix(y_test, tree_pred))

Decision Tree
Accuracy: 0.8994108662448178
Precision: 0.9273564847625797
Recall: 0.9108945353289245
F1: 0.9190517998244073
Confusion Matrix:
[[1505  205]
 [ 256 2617]]

influences = (pd.DataFrame({'importance': tree.feature_importances_,
                           'feature': X_train.columns})
                           .sort_values('importance')
                           .query('importance >= 0.02'))

(
ggplot(data = influences, mapping = aes(x = 'feature', y = 'importance'))
  + geom_bar(stat = 'identity') 
  + coord_flip()
  + labs(
    x = "Feature",
    y = "Importance",
    title = "Decision Tree Classifier Feature Importance"
  )
  + theme(plot_title=element_text(size=15,hjust=-1.3))
)

# RANDOM FOREST
from sklearn.ensemble import RandomForestClassifier

forest = RandomForestClassifier()
forest.fit(X_train, y_train)
forest_pred = forest.predict(X_test)

forest_accuracy = accuracy_score(y_test, forest_pred)
forest_precision = precision_score(y_test, forest_pred)
forest_recall = recall_score(y_test, forest_pred)
forest_f1 = f1_score(y_test, forest_pred)

print('Random Forest')
print('Accuracy:', forest_accuracy)
print('Precision:', forest_precision)
print('Recall:', forest_recall)
print('F1:', forest_f1)
print('Confusion Matrix:')
print(confusion_matrix(y_test, forest_pred))

Random Forest
Accuracy: 0.9319223216233908
Precision: 0.9438474870017332
Recall: 0.9477897667942917
F1: 0.9458145189301841
Confusion Matrix:
[[1548  162]
 [ 150 2723]]

influences = (pd.DataFrame({'importance': forest.feature_importances_,
                           'feature': X_train.columns})
                           .sort_values('importance')
                           .query('importance >= 0.02'))

(
ggplot(data = influences, mapping = aes(x = 'feature', y = 'importance'))
  + geom_bar(stat = 'identity') 
  + coord_flip()
  + labs(
    x = "Feature",
    y = "Importance",
    title = "Random Forest Classifier Feature Importance"
  )
  + theme(plot_title=element_text(size=15,hjust=-1.45))
)

# NEURAL NETWORK
import tensorflow as tf
from tensorflow import keras
from keras import Input, Model

norm = MinMaxScaler().fit(X_train)
X_train = norm.transform(X_train)
X_test = norm.transform(X_test)

model = Sequential()
model.add(Input(shape=(len(X_train[0]),)))
model.add(Dense(16, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

opt = keras.optimizers.Adam()
model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])

early_stop = keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)

history = model.fit(X_train, y_train, epochs=2000, validation_split=.2, batch_size=32, callbacks=[early_stop],shuffle=False)

hist = pd.DataFrame(history.history)

hist = hist.reset_index()

predictions = model.predict(X_test)
binary_predictions = (predictions >= 0.5).astype(int)

nn_accuracy = accuracy_score(y_test, binary_predictions)
nn_precision = precision_score(y_test, binary_predictions)
nn_recall = recall_score(y_test, binary_predictions)
nn_f1 = f1_score(y_test, binary_predictions)

print('Neural Network')
print('Accuracy:', nn_accuracy)
print('Precision:', nn_precision)
print('Recall:', nn_recall)
print('F1:', nn_f1)
print('Confusion Matrix:')
print(confusion_matrix(y_test, binary_predictions))

Epoch 1/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 13:18 2s/step - accuracy: 0.5938 - loss: 0.6819 28/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.5912 - loss: 0.6703   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6157 - loss: 0.6542 83/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6269 - loss: 0.6405107/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6342 - loss: 0.6294127/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6414 - loss: 0.6206147/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6491 - loss: 0.6117166/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6564 - loss: 0.6035189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6648 - loss: 0.5943213/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6732 - loss: 0.5851236/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6806 - loss: 0.5769258/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6873 - loss: 0.5693288/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6958 - loss: 0.5595320/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7040 - loss: 0.5497346/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7102 - loss: 0.5422366/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7146 - loss: 0.5367388/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7191 - loss: 0.5310420/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7252 - loss: 0.5233451/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7306 - loss: 0.5162459/459 ━━━━━━━━━━━━━━━━━━━━ 3s 3ms/step - accuracy: 0.7321 - loss: 0.5142 - val_accuracy: 0.8582 - val_loss: 0.3444
Epoch 2/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 0.9375 - loss: 0.1909 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8706 - loss: 0.3107   51/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8726 - loss: 0.3084 78/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8710 - loss: 0.3112108/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8696 - loss: 0.3139138/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8690 - loss: 0.3157168/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8690 - loss: 0.3164198/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8687 - loss: 0.3173227/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8683 - loss: 0.3182256/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8680 - loss: 0.3189285/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8679 - loss: 0.3194312/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8678 - loss: 0.3197338/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8677 - loss: 0.3198373/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8678 - loss: 0.3198410/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8678 - loss: 0.3197440/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8679 - loss: 0.3195459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8680 - loss: 0.3193 - val_accuracy: 0.8672 - val_loss: 0.3256
Epoch 3/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 38ms/step - accuracy: 0.9375 - loss: 0.1571 33/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8734 - loss: 0.2908   67/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8759 - loss: 0.2924 87/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8754 - loss: 0.2947119/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8747 - loss: 0.2972152/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8745 - loss: 0.2990182/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8744 - loss: 0.2999215/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8740 - loss: 0.3011239/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8736 - loss: 0.3021266/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8733 - loss: 0.3028290/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8732 - loss: 0.3033320/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8731 - loss: 0.3038352/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8730 - loss: 0.3041386/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8729 - loss: 0.3043419/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8729 - loss: 0.3044442/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8729 - loss: 0.3043459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8730 - loss: 0.3043 - val_accuracy: 0.8702 - val_loss: 0.3173
Epoch 4/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.9688 - loss: 0.1395 33/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8744 - loss: 0.2824   63/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8769 - loss: 0.2837 93/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8766 - loss: 0.2874119/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8763 - loss: 0.2892150/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8762 - loss: 0.2910182/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8761 - loss: 0.2921218/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8757 - loss: 0.2935257/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8752 - loss: 0.2950295/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8751 - loss: 0.2958324/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8750 - loss: 0.2963353/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8749 - loss: 0.2967381/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8749 - loss: 0.2969411/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8748 - loss: 0.2971442/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8748 - loss: 0.2971459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8748 - loss: 0.2971 - val_accuracy: 0.8718 - val_loss: 0.3118
Epoch 5/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 37ms/step - accuracy: 0.9688 - loss: 0.1303 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8751 - loss: 0.2776   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8801 - loss: 0.2768 82/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8794 - loss: 0.2804108/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8787 - loss: 0.2829135/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8783 - loss: 0.2848166/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8781 - loss: 0.2861195/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8778 - loss: 0.2872221/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8774 - loss: 0.2884247/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8770 - loss: 0.2894278/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8769 - loss: 0.2903307/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8768 - loss: 0.2909332/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8767 - loss: 0.2913355/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8766 - loss: 0.2916383/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8765 - loss: 0.2919411/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8764 - loss: 0.2921443/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8764 - loss: 0.2922459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8764 - loss: 0.2922 - val_accuracy: 0.8732 - val_loss: 0.3081
Epoch 6/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 27s 61ms/step - accuracy: 0.9688 - loss: 0.1251 27/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8790 - loss: 0.2731   49/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8836 - loss: 0.2720 72/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8824 - loss: 0.2753 90/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8815 - loss: 0.2774116/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8802 - loss: 0.2794142/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8795 - loss: 0.2810166/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8792 - loss: 0.2819191/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8788 - loss: 0.2829219/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8784 - loss: 0.2841246/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8780 - loss: 0.2852277/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8779 - loss: 0.2862306/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8778 - loss: 0.2868341/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8776 - loss: 0.2874371/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8775 - loss: 0.2878402/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8774 - loss: 0.2881433/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8774 - loss: 0.2883459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8774 - loss: 0.2883 - val_accuracy: 0.8726 - val_loss: 0.3050
Epoch 7/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 37ms/step - accuracy: 0.9688 - loss: 0.1215 25/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8866 - loss: 0.2702   49/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8904 - loss: 0.2685 76/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8877 - loss: 0.2721108/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8851 - loss: 0.2751143/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8835 - loss: 0.2774176/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8826 - loss: 0.2788207/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8820 - loss: 0.2799239/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8812 - loss: 0.2814270/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8809 - loss: 0.2825302/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8806 - loss: 0.2833329/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8804 - loss: 0.2838350/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8802 - loss: 0.2841375/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8800 - loss: 0.2845402/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8799 - loss: 0.2847430/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8797 - loss: 0.2849451/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8797 - loss: 0.2849459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8797 - loss: 0.2849 - val_accuracy: 0.8726 - val_loss: 0.3023
Epoch 8/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 23s 51ms/step - accuracy: 0.9688 - loss: 0.1186 21/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8843 - loss: 0.2676   43/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8898 - loss: 0.2656 69/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8882 - loss: 0.2685 92/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8866 - loss: 0.2711116/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8852 - loss: 0.2727143/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8843 - loss: 0.2744170/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8837 - loss: 0.2754202/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8831 - loss: 0.2767234/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8824 - loss: 0.2782264/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8820 - loss: 0.2793294/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8817 - loss: 0.2801326/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8814 - loss: 0.2808359/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8812 - loss: 0.2814387/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8810 - loss: 0.2817421/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8808 - loss: 0.2820452/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8807 - loss: 0.2821459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8807 - loss: 0.2821 - val_accuracy: 0.8751 - val_loss: 0.2997
Epoch 9/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 28s 61ms/step - accuracy: 0.9688 - loss: 0.1170 21/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8850 - loss: 0.2654   42/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8917 - loss: 0.2634 68/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8904 - loss: 0.2660102/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8880 - loss: 0.2693135/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8865 - loss: 0.2714166/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8856 - loss: 0.2727202/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8848 - loss: 0.2742236/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8841 - loss: 0.2758264/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8838 - loss: 0.2768289/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8835 - loss: 0.2775311/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8833 - loss: 0.2780336/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8830 - loss: 0.2785366/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8827 - loss: 0.2790402/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8824 - loss: 0.2794437/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8822 - loss: 0.2797459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8821 - loss: 0.2797 - val_accuracy: 0.8770 - val_loss: 0.2975
Epoch 10/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 25s 56ms/step - accuracy: 0.9688 - loss: 0.1142 23/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8868 - loss: 0.2628   47/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2608 78/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8907 - loss: 0.2647104/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8888 - loss: 0.2671122/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8879 - loss: 0.2682140/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8871 - loss: 0.2693164/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8864 - loss: 0.2703188/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8859 - loss: 0.2712211/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8854 - loss: 0.2722230/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8850 - loss: 0.2732256/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8846 - loss: 0.2742284/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8844 - loss: 0.2750308/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8841 - loss: 0.2757335/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8839 - loss: 0.2762369/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8835 - loss: 0.2768400/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8833 - loss: 0.2772432/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8831 - loss: 0.2775459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8830 - loss: 0.2775 - val_accuracy: 0.8778 - val_loss: 0.2956
Epoch 11/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.9688 - loss: 0.1120 37/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8934 - loss: 0.2592   73/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8927 - loss: 0.2621101/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8906 - loss: 0.2648131/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8890 - loss: 0.2667162/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8879 - loss: 0.2682193/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8870 - loss: 0.2693227/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8861 - loss: 0.2709259/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8856 - loss: 0.2722287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8853 - loss: 0.2731309/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8850 - loss: 0.2736330/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8848 - loss: 0.2741359/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8845 - loss: 0.2746379/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8842 - loss: 0.2749403/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8840 - loss: 0.2752437/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8838 - loss: 0.2755459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8837 - loss: 0.2756 - val_accuracy: 0.8797 - val_loss: 0.2937
Epoch 12/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 20s 44ms/step - accuracy: 0.9688 - loss: 0.1105 25/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8915 - loss: 0.2580   43/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8959 - loss: 0.2568 68/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.2596 93/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2624123/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8904 - loss: 0.2642153/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8891 - loss: 0.2659189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8881 - loss: 0.2672226/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8871 - loss: 0.2689257/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8866 - loss: 0.2702287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8862 - loss: 0.2711319/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8859 - loss: 0.2719343/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8856 - loss: 0.2724368/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8854 - loss: 0.2729393/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8852 - loss: 0.2732417/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8850 - loss: 0.2735448/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8848 - loss: 0.2737459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8848 - loss: 0.2737 - val_accuracy: 0.8803 - val_loss: 0.2921
Epoch 13/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 42ms/step - accuracy: 0.9688 - loss: 0.1089 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8888 - loss: 0.2554   55/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.2555 82/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8919 - loss: 0.2593114/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8901 - loss: 0.2619148/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8889 - loss: 0.2638181/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8880 - loss: 0.2651213/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8873 - loss: 0.2664232/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8869 - loss: 0.2674253/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8866 - loss: 0.2682270/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8864 - loss: 0.2688287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8862 - loss: 0.2693308/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8860 - loss: 0.2699333/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8858 - loss: 0.2705355/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8855 - loss: 0.2709380/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8853 - loss: 0.2713414/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8850 - loss: 0.2717441/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8849 - loss: 0.2719459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8848 - loss: 0.2720 - val_accuracy: 0.8811 - val_loss: 0.2910
Epoch 14/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 33ms/step - accuracy: 0.9688 - loss: 0.1081 35/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2536   64/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2555 94/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8927 - loss: 0.2590127/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8913 - loss: 0.2610158/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8901 - loss: 0.2625180/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8895 - loss: 0.2634204/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8888 - loss: 0.2643228/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8882 - loss: 0.2655252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8878 - loss: 0.2665286/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8873 - loss: 0.2677320/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8869 - loss: 0.2686351/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8865 - loss: 0.2692386/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8862 - loss: 0.2698415/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8860 - loss: 0.2702439/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8858 - loss: 0.2704459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8858 - loss: 0.2705 - val_accuracy: 0.8819 - val_loss: 0.2895
Epoch 15/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 0.9688 - loss: 0.1071 31/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8918 - loss: 0.2513   59/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2529 91/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8926 - loss: 0.2570126/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8912 - loss: 0.2592161/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8902 - loss: 0.2610195/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8895 - loss: 0.2622221/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8889 - loss: 0.2635241/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8886 - loss: 0.2644267/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8883 - loss: 0.2654287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8881 - loss: 0.2660312/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8878 - loss: 0.2667342/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8875 - loss: 0.2674377/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8871 - loss: 0.2680407/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8869 - loss: 0.2684439/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8867 - loss: 0.2688459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8866 - loss: 0.2688 - val_accuracy: 0.8838 - val_loss: 0.2879
Epoch 16/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 35ms/step - accuracy: 0.9688 - loss: 0.1068 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8909 - loss: 0.2501   66/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2527 97/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2560132/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8915 - loss: 0.2581162/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8910 - loss: 0.2594186/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8905 - loss: 0.2603207/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8902 - loss: 0.2612231/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8897 - loss: 0.2624248/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8895 - loss: 0.2631275/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8892 - loss: 0.2641296/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8890 - loss: 0.2648313/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8888 - loss: 0.2652334/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8886 - loss: 0.2657357/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8883 - loss: 0.2661380/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8881 - loss: 0.2665396/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8880 - loss: 0.2668413/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8878 - loss: 0.2670431/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8877 - loss: 0.2672445/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8876 - loss: 0.2673459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8876 - loss: 0.2674 - val_accuracy: 0.8852 - val_loss: 0.2866
Epoch 17/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 0.9688 - loss: 0.1057 25/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8878 - loss: 0.2493   45/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2485 73/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2520100/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8923 - loss: 0.2548118/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8919 - loss: 0.2558134/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8916 - loss: 0.2568150/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8913 - loss: 0.2576168/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8911 - loss: 0.2582188/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8907 - loss: 0.2590205/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8905 - loss: 0.2597221/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8902 - loss: 0.2605237/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8900 - loss: 0.2613253/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8898 - loss: 0.2619270/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8896 - loss: 0.2626287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8894 - loss: 0.2631305/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8892 - loss: 0.2636326/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8890 - loss: 0.2642347/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8888 - loss: 0.2646374/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8885 - loss: 0.2651406/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8882 - loss: 0.2656435/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8880 - loss: 0.2659459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8879 - loss: 0.2660 - val_accuracy: 0.8868 - val_loss: 0.2858
Epoch 18/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 24s 53ms/step - accuracy: 0.9688 - loss: 0.1036 30/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8914 - loss: 0.2458   50/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2467 69/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2498 91/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2526119/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8924 - loss: 0.2544147/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8919 - loss: 0.2561177/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8914 - loss: 0.2572203/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8910 - loss: 0.2583231/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8906 - loss: 0.2597262/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8902 - loss: 0.2610290/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8900 - loss: 0.2620313/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8897 - loss: 0.2626339/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8894 - loss: 0.2632361/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8892 - loss: 0.2636386/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8890 - loss: 0.2641418/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8887 - loss: 0.2646443/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8885 - loss: 0.2648459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8884 - loss: 0.2649 - val_accuracy: 0.8852 - val_loss: 0.2852
Epoch 19/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 37ms/step - accuracy: 0.9688 - loss: 0.1027 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8924 - loss: 0.2448   66/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2481 99/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2520131/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8929 - loss: 0.2540162/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8925 - loss: 0.2555191/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8921 - loss: 0.2566223/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8916 - loss: 0.2581254/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8913 - loss: 0.2596287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8910 - loss: 0.2607309/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8908 - loss: 0.2614327/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8906 - loss: 0.2618349/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8904 - loss: 0.2623382/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8900 - loss: 0.2629415/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8897 - loss: 0.2635447/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8896 - loss: 0.2637459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8895 - loss: 0.2638 - val_accuracy: 0.8854 - val_loss: 0.2850
Epoch 20/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.9688 - loss: 0.1022 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8898 - loss: 0.2441   55/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2452 75/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2485101/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.2513123/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2526145/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2539165/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2547182/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2554199/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8928 - loss: 0.2560224/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8925 - loss: 0.2573252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2586277/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8919 - loss: 0.2595295/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8918 - loss: 0.2601319/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8915 - loss: 0.2607349/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8912 - loss: 0.2614375/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8909 - loss: 0.2619395/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8907 - loss: 0.2622411/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8905 - loss: 0.2625428/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8904 - loss: 0.2627445/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8903 - loss: 0.2628459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8903 - loss: 0.2629 - val_accuracy: 0.8854 - val_loss: 0.2848
Epoch 21/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 0.9688 - loss: 0.1018 31/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8925 - loss: 0.2423   57/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8957 - loss: 0.2444 84/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8950 - loss: 0.2486107/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2505138/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8940 - loss: 0.2525168/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2538200/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2551233/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8929 - loss: 0.2568257/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8927 - loss: 0.2578279/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8925 - loss: 0.2586310/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2595337/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8919 - loss: 0.2602361/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8916 - loss: 0.2607386/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8913 - loss: 0.2611407/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8911 - loss: 0.2615433/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8909 - loss: 0.2618459/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8908 - loss: 0.2620459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8908 - loss: 0.2620 - val_accuracy: 0.8854 - val_loss: 0.2845
Epoch 22/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 30s 66ms/step - accuracy: 0.9688 - loss: 0.1001 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8892 - loss: 0.2415   54/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8948 - loss: 0.2429 84/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.2477117/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2503142/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8936 - loss: 0.2519165/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8935 - loss: 0.2528191/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8932 - loss: 0.2539216/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2551240/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8927 - loss: 0.2563269/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8925 - loss: 0.2574298/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8923 - loss: 0.2584323/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8920 - loss: 0.2590346/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8918 - loss: 0.2596365/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8916 - loss: 0.2599384/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8914 - loss: 0.2603410/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8912 - loss: 0.2607439/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8910 - loss: 0.2610459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8909 - loss: 0.2612 - val_accuracy: 0.8860 - val_loss: 0.2840
Epoch 23/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 38ms/step - accuracy: 0.9688 - loss: 0.1008 37/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8927 - loss: 0.2411   73/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8944 - loss: 0.2453110/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8939 - loss: 0.2490142/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8940 - loss: 0.2511176/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8938 - loss: 0.2524211/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8935 - loss: 0.2539252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8931 - loss: 0.2559290/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8929 - loss: 0.2573324/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8925 - loss: 0.2582355/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8922 - loss: 0.2589381/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8920 - loss: 0.2594408/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8917 - loss: 0.2598432/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8915 - loss: 0.2601459/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8915 - loss: 0.2603459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8914 - loss: 0.2603 - val_accuracy: 0.8865 - val_loss: 0.2835
Epoch 24/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 0.9688 - loss: 0.0983 28/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8917 - loss: 0.2378   55/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8966 - loss: 0.2402 87/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8958 - loss: 0.2455120/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8955 - loss: 0.2480149/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2499175/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8950 - loss: 0.2510203/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2521223/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2532242/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2542264/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.2551292/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2561322/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2569351/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2576371/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8928 - loss: 0.2580390/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8926 - loss: 0.2583412/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8924 - loss: 0.2587439/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2590459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8922 - loss: 0.2592 - val_accuracy: 0.8863 - val_loss: 0.2831
Epoch 25/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 23s 52ms/step - accuracy: 0.9688 - loss: 0.0981 35/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2375   65/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8957 - loss: 0.2412100/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2457135/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8951 - loss: 0.2481174/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8949 - loss: 0.2499207/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8946 - loss: 0.2514244/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8941 - loss: 0.2533281/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8938 - loss: 0.2548317/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8934 - loss: 0.2559350/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8930 - loss: 0.2567381/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8927 - loss: 0.2573417/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8924 - loss: 0.2579448/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8922 - loss: 0.2582459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8922 - loss: 0.2582 - val_accuracy: 0.8863 - val_loss: 0.2825
Epoch 26/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 26s 58ms/step - accuracy: 0.9688 - loss: 0.0969 24/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8872 - loss: 0.2350   50/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8943 - loss: 0.2370 78/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2420100/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8943 - loss: 0.2446120/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2460139/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2474163/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2485189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8943 - loss: 0.2497220/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8940 - loss: 0.2513249/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2527278/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8935 - loss: 0.2539300/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2546327/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2554356/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8928 - loss: 0.2560389/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8925 - loss: 0.2566422/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8923 - loss: 0.2572443/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2574459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8921 - loss: 0.2575 - val_accuracy: 0.8871 - val_loss: 0.2827
Epoch 27/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 42ms/step - accuracy: 0.9688 - loss: 0.0964 28/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8896 - loss: 0.2346   47/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.2362 66/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2398 92/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2436116/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8943 - loss: 0.2453141/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2470173/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2484200/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2496229/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2512260/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8936 - loss: 0.2526288/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2536316/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2545350/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8927 - loss: 0.2553382/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8924 - loss: 0.2559416/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2565445/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8921 - loss: 0.2568459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8920 - loss: 0.2569 - val_accuracy: 0.8879 - val_loss: 0.2828
Epoch 28/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 35ms/step - accuracy: 0.9688 - loss: 0.0965 27/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8873 - loss: 0.2349   53/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2370 82/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2420107/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2444131/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2460154/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8935 - loss: 0.2473184/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2486214/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8932 - loss: 0.2500247/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8929 - loss: 0.2516274/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8927 - loss: 0.2527294/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8926 - loss: 0.2534319/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8924 - loss: 0.2541347/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2548377/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8920 - loss: 0.2553407/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8918 - loss: 0.2558433/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8917 - loss: 0.2562459/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8916 - loss: 0.2564459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8916 - loss: 0.2564 - val_accuracy: 0.8876 - val_loss: 0.2826
Epoch 29/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 0.9688 - loss: 0.0967 31/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8890 - loss: 0.2341   57/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2371 81/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2413112/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2441144/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2462176/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2476205/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2488230/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2502256/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8932 - loss: 0.2513281/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2523309/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8929 - loss: 0.2532337/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8926 - loss: 0.2539366/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8924 - loss: 0.2545397/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8923 - loss: 0.2551425/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8921 - loss: 0.2555459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8920 - loss: 0.2558 - val_accuracy: 0.8871 - val_loss: 0.2826
Epoch 30/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 34ms/step - accuracy: 0.9688 - loss: 0.0965 29/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8866 - loss: 0.2326   53/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8918 - loss: 0.2353 75/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8920 - loss: 0.2395103/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8923 - loss: 0.2427131/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2446163/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2462194/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2475219/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2488243/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2500264/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2509288/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8929 - loss: 0.2518307/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8928 - loss: 0.2524327/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8927 - loss: 0.2529347/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8926 - loss: 0.2534369/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8924 - loss: 0.2538391/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8923 - loss: 0.2542410/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8922 - loss: 0.2545439/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8921 - loss: 0.2549459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8921 - loss: 0.2551 - val_accuracy: 0.8868 - val_loss: 0.2822
Epoch 31/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 28s 63ms/step - accuracy: 0.9688 - loss: 0.0960 19/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8830 - loss: 0.2290   37/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8907 - loss: 0.2330 55/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8933 - loss: 0.2346 75/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8934 - loss: 0.2385103/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8937 - loss: 0.2418122/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8942 - loss: 0.2430140/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8944 - loss: 0.2443158/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8945 - loss: 0.2452178/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8946 - loss: 0.2461204/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8945 - loss: 0.2472228/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.8944 - loss: 0.2485252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.2496282/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2508314/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.2518350/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8936 - loss: 0.2527377/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2532405/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2537433/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2541459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8930 - loss: 0.2543 - val_accuracy: 0.8873 - val_loss: 0.2823
Epoch 32/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 0.9688 - loss: 0.0948 27/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8862 - loss: 0.2305   51/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8924 - loss: 0.2334 71/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8927 - loss: 0.2374 93/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8930 - loss: 0.2406123/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2426149/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8940 - loss: 0.2443177/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.2456200/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.2465224/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2478250/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2490277/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.2501302/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2510332/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8936 - loss: 0.2518366/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8935 - loss: 0.2525390/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2529418/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8932 - loss: 0.2534437/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2536455/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2537459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8931 - loss: 0.2538 - val_accuracy: 0.8873 - val_loss: 0.2823
Epoch 33/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 33ms/step - accuracy: 0.9688 - loss: 0.0945 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8918 - loss: 0.2312   64/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8936 - loss: 0.2357 87/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8934 - loss: 0.2393105/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8935 - loss: 0.2408124/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.2421148/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2437177/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2450203/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2461226/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.2473249/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2484272/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2494301/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8935 - loss: 0.2503334/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8933 - loss: 0.2512371/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8931 - loss: 0.2520405/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8929 - loss: 0.2526442/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8928 - loss: 0.2531459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8927 - loss: 0.2532 - val_accuracy: 0.8873 - val_loss: 0.2819
Epoch 34/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 37ms/step - accuracy: 0.9688 - loss: 0.0940 31/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8926 - loss: 0.2297   57/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8954 - loss: 0.2336 81/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8951 - loss: 0.2380105/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8951 - loss: 0.2405129/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8953 - loss: 0.2421153/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8954 - loss: 0.2436172/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8954 - loss: 0.2443192/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8953 - loss: 0.2452212/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2461236/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8950 - loss: 0.2474264/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8948 - loss: 0.2486293/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2497323/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8943 - loss: 0.2505348/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2511370/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8940 - loss: 0.2515394/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8938 - loss: 0.2520414/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8937 - loss: 0.2523432/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8936 - loss: 0.2526451/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8936 - loss: 0.2527459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8936 - loss: 0.2528 - val_accuracy: 0.8871 - val_loss: 0.2820
Epoch 35/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 28s 62ms/step - accuracy: 0.9688 - loss: 0.0938 24/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8898 - loss: 0.2290   52/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2323 79/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2374103/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2400128/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8955 - loss: 0.2417160/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8956 - loss: 0.2434190/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8956 - loss: 0.2447223/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8954 - loss: 0.2463246/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2474272/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8950 - loss: 0.2485306/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8948 - loss: 0.2496343/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8945 - loss: 0.2505380/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.2513417/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8940 - loss: 0.2519450/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8939 - loss: 0.2522459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8939 - loss: 0.2523 - val_accuracy: 0.8865 - val_loss: 0.2812
Epoch 36/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 21s 46ms/step - accuracy: 0.9688 - loss: 0.0948 29/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8918 - loss: 0.2287   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8953 - loss: 0.2326 84/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8950 - loss: 0.2377112/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8951 - loss: 0.2401143/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8954 - loss: 0.2421171/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8956 - loss: 0.2433207/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8955 - loss: 0.2448243/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2467274/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8950 - loss: 0.2479302/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8948 - loss: 0.2489332/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2497359/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8944 - loss: 0.2503386/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8943 - loss: 0.2508411/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8942 - loss: 0.2512439/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8941 - loss: 0.2516459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8941 - loss: 0.2517 - val_accuracy: 0.8860 - val_loss: 0.2813
Epoch 37/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 0.9688 - loss: 0.0948 35/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8989 - loss: 0.2295   70/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8986 - loss: 0.2350 97/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8979 - loss: 0.2386122/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8979 - loss: 0.2402155/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8977 - loss: 0.2422185/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8976 - loss: 0.2435212/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8973 - loss: 0.2447237/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8970 - loss: 0.2460259/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8968 - loss: 0.2469278/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8965 - loss: 0.2477299/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8963 - loss: 0.2484319/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8961 - loss: 0.2489347/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8958 - loss: 0.2496380/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8956 - loss: 0.2502413/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8953 - loss: 0.2508441/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8951 - loss: 0.2511459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8951 - loss: 0.2512 - val_accuracy: 0.8860 - val_loss: 0.2811
Epoch 38/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 0.9688 - loss: 0.0936 31/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8985 - loss: 0.2274   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8990 - loss: 0.2312 85/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8976 - loss: 0.2366117/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8972 - loss: 0.2391152/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8970 - loss: 0.2414189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8968 - loss: 0.2429223/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8964 - loss: 0.2446254/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8961 - loss: 0.2460278/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8958 - loss: 0.2470302/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8956 - loss: 0.2478323/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8954 - loss: 0.2484345/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2489380/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8949 - loss: 0.2496416/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8946 - loss: 0.2502449/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8945 - loss: 0.2505459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8945 - loss: 0.2506 - val_accuracy: 0.8868 - val_loss: 0.2803
Epoch 39/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 25s 55ms/step - accuracy: 0.9688 - loss: 0.0944 22/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8953 - loss: 0.2251   45/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8984 - loss: 0.2288 67/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8974 - loss: 0.2331 95/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8967 - loss: 0.2371128/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8966 - loss: 0.2393155/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8965 - loss: 0.2409175/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8965 - loss: 0.2417204/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8963 - loss: 0.2430232/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8960 - loss: 0.2445271/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8956 - loss: 0.2461310/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8953 - loss: 0.2474350/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8949 - loss: 0.2484385/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8947 - loss: 0.2491419/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8945 - loss: 0.2497447/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8945 - loss: 0.2500459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8944 - loss: 0.2500 - val_accuracy: 0.8868 - val_loss: 0.2803
Epoch 40/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 13s 30ms/step - accuracy: 0.9688 - loss: 0.0936 37/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8976 - loss: 0.2279   76/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8972 - loss: 0.2342114/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8967 - loss: 0.2380145/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8967 - loss: 0.2400180/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8966 - loss: 0.2415216/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8964 - loss: 0.2432253/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8961 - loss: 0.2450291/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8958 - loss: 0.2464330/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8955 - loss: 0.2475363/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8953 - loss: 0.2483393/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8952 - loss: 0.2488425/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8950 - loss: 0.2493455/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8950 - loss: 0.2496459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8950 - loss: 0.2496 - val_accuracy: 0.8868 - val_loss: 0.2799
Epoch 41/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 23s 51ms/step - accuracy: 1.0000 - loss: 0.0932 20/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9002 - loss: 0.2227   51/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9004 - loss: 0.2289 82/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8984 - loss: 0.2348112/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8975 - loss: 0.2376134/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8973 - loss: 0.2391158/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8972 - loss: 0.2403187/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8969 - loss: 0.2415220/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8966 - loss: 0.2431250/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8963 - loss: 0.2445275/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8960 - loss: 0.2456304/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8958 - loss: 0.2465335/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8955 - loss: 0.2473370/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8952 - loss: 0.2480397/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8951 - loss: 0.2485422/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8949 - loss: 0.2489449/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8948 - loss: 0.2492459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8948 - loss: 0.2492 - val_accuracy: 0.8865 - val_loss: 0.2798
Epoch 42/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 33ms/step - accuracy: 1.0000 - loss: 0.0924 39/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9015 - loss: 0.2273   73/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8995 - loss: 0.2330111/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8981 - loss: 0.2370139/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8978 - loss: 0.2389170/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8975 - loss: 0.2403195/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8973 - loss: 0.2414221/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8970 - loss: 0.2427246/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8967 - loss: 0.2439273/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8964 - loss: 0.2450302/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8961 - loss: 0.2460334/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8958 - loss: 0.2469366/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8956 - loss: 0.2475402/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8953 - loss: 0.2482435/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8951 - loss: 0.2486457/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8950 - loss: 0.2488459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8950 - loss: 0.2488 - val_accuracy: 0.8876 - val_loss: 0.2792
Epoch 43/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 34ms/step - accuracy: 1.0000 - loss: 0.0914 35/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9066 - loss: 0.2257   71/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9030 - loss: 0.2318112/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9005 - loss: 0.2363151/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8997 - loss: 0.2389185/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8991 - loss: 0.2403220/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8985 - loss: 0.2420256/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8979 - loss: 0.2437291/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8974 - loss: 0.2451326/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8970 - loss: 0.2461364/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8966 - loss: 0.2469403/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8962 - loss: 0.2476440/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.8959 - loss: 0.2481459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8959 - loss: 0.2483 - val_accuracy: 0.8871 - val_loss: 0.2787
Epoch 44/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 34ms/step - accuracy: 1.0000 - loss: 0.0898 38/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9081 - loss: 0.2249   70/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9043 - loss: 0.2305101/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9019 - loss: 0.2346133/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9009 - loss: 0.2369164/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2386197/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8996 - loss: 0.2400223/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8991 - loss: 0.2415247/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8986 - loss: 0.2426278/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8982 - loss: 0.2439312/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8976 - loss: 0.2450344/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8972 - loss: 0.2459376/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8969 - loss: 0.2465409/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8966 - loss: 0.2471441/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8963 - loss: 0.2475459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8963 - loss: 0.2477 - val_accuracy: 0.8873 - val_loss: 0.2785
Epoch 45/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 1.0000 - loss: 0.0898 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2231   63/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9043 - loss: 0.2288 92/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9020 - loss: 0.2336124/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2358158/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9001 - loss: 0.2379189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8996 - loss: 0.2393218/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8991 - loss: 0.2407241/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8987 - loss: 0.2419265/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8984 - loss: 0.2430285/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8981 - loss: 0.2437304/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8979 - loss: 0.2444333/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8975 - loss: 0.2452362/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8972 - loss: 0.2458386/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8970 - loss: 0.2462409/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8968 - loss: 0.2466442/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8965 - loss: 0.2471459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8965 - loss: 0.2472 - val_accuracy: 0.8868 - val_loss: 0.2784
Epoch 46/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 39ms/step - accuracy: 1.0000 - loss: 0.0895 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2222   66/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9026 - loss: 0.2287 96/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9011 - loss: 0.2332125/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2353158/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9000 - loss: 0.2373183/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8997 - loss: 0.2385209/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8994 - loss: 0.2397235/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8990 - loss: 0.2411260/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8986 - loss: 0.2422290/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8983 - loss: 0.2434323/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8979 - loss: 0.2444354/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8975 - loss: 0.2451385/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8972 - loss: 0.2457413/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8970 - loss: 0.2462445/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8968 - loss: 0.2466459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8967 - loss: 0.2467 - val_accuracy: 0.8868 - val_loss: 0.2784
Epoch 47/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 21s 46ms/step - accuracy: 1.0000 - loss: 0.0892 28/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2209   59/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9029 - loss: 0.2267 87/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2318116/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2342150/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8996 - loss: 0.2366181/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8992 - loss: 0.2380211/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8989 - loss: 0.2394241/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8984 - loss: 0.2410279/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8980 - loss: 0.2426314/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8976 - loss: 0.2437347/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8972 - loss: 0.2446371/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8970 - loss: 0.2450398/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8967 - loss: 0.2455430/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8965 - loss: 0.2460459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8964 - loss: 0.2463 - val_accuracy: 0.8857 - val_loss: 0.2785
Epoch 48/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 22s 49ms/step - accuracy: 1.0000 - loss: 0.0893 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9067 - loss: 0.2200   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2252 78/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9030 - loss: 0.2297104/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2328130/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9013 - loss: 0.2347162/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9009 - loss: 0.2365190/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9005 - loss: 0.2378217/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2392241/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8998 - loss: 0.2405266/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8995 - loss: 0.2416290/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8992 - loss: 0.2425322/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8987 - loss: 0.2435351/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8984 - loss: 0.2442376/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8982 - loss: 0.2447405/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8979 - loss: 0.2452434/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8977 - loss: 0.2456459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8975 - loss: 0.2458 - val_accuracy: 0.8857 - val_loss: 0.2780
Epoch 49/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 26s 57ms/step - accuracy: 1.0000 - loss: 0.0884 20/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9093 - loss: 0.2165   38/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9074 - loss: 0.2222 64/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2267 90/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9028 - loss: 0.2311110/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9022 - loss: 0.2327130/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2342157/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9012 - loss: 0.2359181/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9008 - loss: 0.2370209/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9005 - loss: 0.2383233/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9001 - loss: 0.2397261/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8997 - loss: 0.2410290/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8992 - loss: 0.2421317/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8989 - loss: 0.2429346/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8985 - loss: 0.2437379/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8982 - loss: 0.2443413/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8978 - loss: 0.2449437/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8976 - loss: 0.2452459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8975 - loss: 0.2454 - val_accuracy: 0.8857 - val_loss: 0.2778
Epoch 50/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 35ms/step - accuracy: 1.0000 - loss: 0.0871 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9083 - loss: 0.2183   49/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2226 71/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2274 97/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9026 - loss: 0.2312122/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9020 - loss: 0.2331144/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9014 - loss: 0.2347169/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2359197/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2373218/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9003 - loss: 0.2384242/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2397273/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8995 - loss: 0.2411304/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8991 - loss: 0.2422335/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8987 - loss: 0.2431363/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8984 - loss: 0.2437385/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8982 - loss: 0.2441408/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8980 - loss: 0.2445441/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8978 - loss: 0.2449459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8977 - loss: 0.2451 - val_accuracy: 0.8865 - val_loss: 0.2777
Epoch 51/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 23s 52ms/step - accuracy: 1.0000 - loss: 0.0870 22/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9088 - loss: 0.2163   45/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2214 68/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9042 - loss: 0.2263 94/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9027 - loss: 0.2304120/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9022 - loss: 0.2324148/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2345172/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9012 - loss: 0.2357200/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9008 - loss: 0.2370225/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9005 - loss: 0.2384256/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9000 - loss: 0.2400287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8996 - loss: 0.2412316/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8992 - loss: 0.2421342/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8989 - loss: 0.2428373/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8986 - loss: 0.2434408/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8983 - loss: 0.2441441/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8980 - loss: 0.2445459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8980 - loss: 0.2447 - val_accuracy: 0.8865 - val_loss: 0.2779
Epoch 52/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 21s 46ms/step - accuracy: 1.0000 - loss: 0.0871 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9081 - loss: 0.2185   55/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2224 86/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9031 - loss: 0.2287116/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9023 - loss: 0.2314141/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2334167/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2348198/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9011 - loss: 0.2363222/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9007 - loss: 0.2377247/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9004 - loss: 0.2390277/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2403310/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8995 - loss: 0.2414343/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8991 - loss: 0.2423368/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8988 - loss: 0.2429400/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8985 - loss: 0.2435431/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8982 - loss: 0.2440454/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8981 - loss: 0.2442459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8981 - loss: 0.2442 - val_accuracy: 0.8863 - val_loss: 0.2779
Epoch 53/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 29s 65ms/step - accuracy: 1.0000 - loss: 0.0871 20/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9120 - loss: 0.2131   45/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9083 - loss: 0.2197 72/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2254104/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9030 - loss: 0.2297135/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9024 - loss: 0.2322171/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2343195/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2354228/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9009 - loss: 0.2374261/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9004 - loss: 0.2390293/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2403324/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8995 - loss: 0.2413358/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8991 - loss: 0.2421391/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8987 - loss: 0.2427420/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8984 - loss: 0.2432448/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8982 - loss: 0.2436459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8982 - loss: 0.2436 - val_accuracy: 0.8863 - val_loss: 0.2777
Epoch 54/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 1.0000 - loss: 0.0858 30/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9101 - loss: 0.2161   58/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9063 - loss: 0.2217 87/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9037 - loss: 0.2275119/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9028 - loss: 0.2303148/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9021 - loss: 0.2326175/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9017 - loss: 0.2340199/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9014 - loss: 0.2351225/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2367251/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2380277/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2392307/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2403331/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8995 - loss: 0.2410362/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8991 - loss: 0.2417395/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8988 - loss: 0.2423419/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8985 - loss: 0.2428448/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8983 - loss: 0.2431459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8983 - loss: 0.2432 - val_accuracy: 0.8879 - val_loss: 0.2773
Epoch 55/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 18s 40ms/step - accuracy: 1.0000 - loss: 0.0868 33/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9122 - loss: 0.2162   64/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9079 - loss: 0.2224 89/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2270110/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2289127/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2303150/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9039 - loss: 0.2321179/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9034 - loss: 0.2336204/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9029 - loss: 0.2348231/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9024 - loss: 0.2365254/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9019 - loss: 0.2376283/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9014 - loss: 0.2389313/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2399339/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9005 - loss: 0.2407366/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2413390/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2417416/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8996 - loss: 0.2422441/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8993 - loss: 0.2425459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8992 - loss: 0.2427 - val_accuracy: 0.8876 - val_loss: 0.2773
Epoch 56/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 1.0000 - loss: 0.0863 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9128 - loss: 0.2162   61/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2213 89/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9061 - loss: 0.2267111/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2288135/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2308155/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2321180/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9035 - loss: 0.2334208/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9030 - loss: 0.2348235/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9024 - loss: 0.2365263/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9019 - loss: 0.2378297/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9013 - loss: 0.2392328/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9008 - loss: 0.2401362/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9004 - loss: 0.2409395/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9000 - loss: 0.2416431/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8996 - loss: 0.2422459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8994 - loss: 0.2424 - val_accuracy: 0.8876 - val_loss: 0.2769
Epoch 57/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 37ms/step - accuracy: 1.0000 - loss: 0.0861 31/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9135 - loss: 0.2145   61/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9090 - loss: 0.2208 89/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9063 - loss: 0.2262117/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2288142/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2309168/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2323193/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9036 - loss: 0.2336219/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9031 - loss: 0.2352246/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9025 - loss: 0.2366270/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9021 - loss: 0.2378299/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9016 - loss: 0.2389333/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9011 - loss: 0.2399365/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9007 - loss: 0.2406394/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9003 - loss: 0.2412431/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2418459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8997 - loss: 0.2420 - val_accuracy: 0.8871 - val_loss: 0.2765
Epoch 58/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 37ms/step - accuracy: 1.0000 - loss: 0.0864 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9130 - loss: 0.2148   62/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9087 - loss: 0.2203 95/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2263131/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2294155/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2311176/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9037 - loss: 0.2322198/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9034 - loss: 0.2333229/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9028 - loss: 0.2352257/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9022 - loss: 0.2366279/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9019 - loss: 0.2376302/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2384334/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2394367/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2401392/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2406417/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9000 - loss: 0.2411440/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8998 - loss: 0.2413459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8996 - loss: 0.2415 - val_accuracy: 0.8873 - val_loss: 0.2763
Epoch 59/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 23s 51ms/step - accuracy: 1.0000 - loss: 0.0860 27/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9142 - loss: 0.2115   53/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9096 - loss: 0.2170 79/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2230104/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2263131/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9042 - loss: 0.2287149/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9037 - loss: 0.2301169/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9034 - loss: 0.2312200/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9028 - loss: 0.2328229/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9023 - loss: 0.2346261/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9017 - loss: 0.2363282/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9013 - loss: 0.2372303/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2379329/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2387356/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2394381/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2399401/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8997 - loss: 0.2402420/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8995 - loss: 0.2406438/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8994 - loss: 0.2408458/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8992 - loss: 0.2409459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8992 - loss: 0.2410 - val_accuracy: 0.8879 - val_loss: 0.2754
Epoch 60/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 1.0000 - loss: 0.0853 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9126 - loss: 0.2135   63/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2194 96/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2252132/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2285168/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9035 - loss: 0.2308200/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9031 - loss: 0.2325224/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9027 - loss: 0.2340252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9022 - loss: 0.2355283/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9017 - loss: 0.2369314/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9013 - loss: 0.2380345/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9009 - loss: 0.2388384/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9005 - loss: 0.2396425/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9001 - loss: 0.2403458/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2406459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8999 - loss: 0.2406 - val_accuracy: 0.8876 - val_loss: 0.2753
Epoch 61/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 37ms/step - accuracy: 1.0000 - loss: 0.0846 28/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9133 - loss: 0.2101   57/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9083 - loss: 0.2168 86/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2232115/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2264139/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9036 - loss: 0.2285162/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9033 - loss: 0.2300187/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9029 - loss: 0.2313209/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9027 - loss: 0.2325233/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9022 - loss: 0.2341259/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2354285/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2365306/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9012 - loss: 0.2373325/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9009 - loss: 0.2379347/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9007 - loss: 0.2384371/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9004 - loss: 0.2389394/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2393419/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9000 - loss: 0.2398448/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8999 - loss: 0.2401459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.8998 - loss: 0.2402 - val_accuracy: 0.8876 - val_loss: 0.2750
Epoch 62/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 20s 44ms/step - accuracy: 1.0000 - loss: 0.0850 29/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9131 - loss: 0.2100   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2161 89/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2233119/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2262145/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9036 - loss: 0.2286173/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9033 - loss: 0.2302200/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9029 - loss: 0.2316230/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9024 - loss: 0.2335260/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9019 - loss: 0.2350286/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9016 - loss: 0.2361311/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9013 - loss: 0.2370336/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9009 - loss: 0.2377362/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2383387/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9004 - loss: 0.2388414/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9001 - loss: 0.2392440/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9000 - loss: 0.2396459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.8999 - loss: 0.2397 - val_accuracy: 0.8882 - val_loss: 0.2747
Epoch 63/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 42ms/step - accuracy: 1.0000 - loss: 0.0848 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9119 - loss: 0.2117   64/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9072 - loss: 0.2181 90/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2232120/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9044 - loss: 0.2261151/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9039 - loss: 0.2287179/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9035 - loss: 0.2302208/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9031 - loss: 0.2317237/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9025 - loss: 0.2335261/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9021 - loss: 0.2347283/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2357305/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2364336/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9011 - loss: 0.2374369/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9008 - loss: 0.2381403/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9005 - loss: 0.2387427/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9003 - loss: 0.2391454/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9002 - loss: 0.2393459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9002 - loss: 0.2393 - val_accuracy: 0.8887 - val_loss: 0.2745
Epoch 64/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 23s 52ms/step - accuracy: 1.0000 - loss: 0.0852 30/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9135 - loss: 0.2099   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9092 - loss: 0.2157 86/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2224115/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2254142/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2278168/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9042 - loss: 0.2293199/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9037 - loss: 0.2309227/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9032 - loss: 0.2326260/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9026 - loss: 0.2343298/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9020 - loss: 0.2359334/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2369363/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9011 - loss: 0.2376390/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9009 - loss: 0.2381425/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2387459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9004 - loss: 0.2390 - val_accuracy: 0.8887 - val_loss: 0.2744
Epoch 65/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 1.0000 - loss: 0.0849 31/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9138 - loss: 0.2094   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9098 - loss: 0.2149 81/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9068 - loss: 0.2208106/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2240129/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2261154/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2280180/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9042 - loss: 0.2294216/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9036 - loss: 0.2314245/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9030 - loss: 0.2330272/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9026 - loss: 0.2343296/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9022 - loss: 0.2353316/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9019 - loss: 0.2359336/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9016 - loss: 0.2365360/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9013 - loss: 0.2370390/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2376419/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9007 - loss: 0.2381440/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2383459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9005 - loss: 0.2385 - val_accuracy: 0.8895 - val_loss: 0.2738
Epoch 66/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 26s 59ms/step - accuracy: 1.0000 - loss: 0.0842 20/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9173 - loss: 0.2047   40/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9122 - loss: 0.2123 66/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9083 - loss: 0.2178 92/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2227123/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2255153/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2279184/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9042 - loss: 0.2295216/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9037 - loss: 0.2312250/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9029 - loss: 0.2331287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9023 - loss: 0.2348320/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2359356/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9013 - loss: 0.2368394/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2375429/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9007 - loss: 0.2381454/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9006 - loss: 0.2383459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9005 - loss: 0.2383 - val_accuracy: 0.8895 - val_loss: 0.2737
Epoch 67/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 21s 48ms/step - accuracy: 1.0000 - loss: 0.0844 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9133 - loss: 0.2107   67/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2178 98/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9067 - loss: 0.2230125/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2254152/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2275176/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2288196/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2297220/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2312244/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9035 - loss: 0.2325267/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9031 - loss: 0.2336289/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9027 - loss: 0.2345318/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9022 - loss: 0.2355346/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2362373/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2368402/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9012 - loss: 0.2373429/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2377459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9008 - loss: 0.2379 - val_accuracy: 0.8895 - val_loss: 0.2738
Epoch 68/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 33ms/step - accuracy: 1.0000 - loss: 0.0844 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9137 - loss: 0.2096   63/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9093 - loss: 0.2165 92/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9069 - loss: 0.2221123/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9061 - loss: 0.2249150/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2271174/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2283203/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2297234/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9038 - loss: 0.2317269/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9031 - loss: 0.2334298/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9027 - loss: 0.2345331/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9021 - loss: 0.2355362/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2362398/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9014 - loss: 0.2369432/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9011 - loss: 0.2374459/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9010 - loss: 0.2376459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9010 - loss: 0.2376 - val_accuracy: 0.8893 - val_loss: 0.2740
Epoch 69/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 24s 53ms/step - accuracy: 1.0000 - loss: 0.0839 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9159 - loss: 0.2077   51/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9122 - loss: 0.2133 77/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9087 - loss: 0.2193101/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9073 - loss: 0.2228127/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2251158/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2273182/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2285205/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2296226/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9044 - loss: 0.2309247/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2320275/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9034 - loss: 0.2334309/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9029 - loss: 0.2346335/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9024 - loss: 0.2353370/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9020 - loss: 0.2361404/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9016 - loss: 0.2367438/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9014 - loss: 0.2372459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9012 - loss: 0.2373 - val_accuracy: 0.8882 - val_loss: 0.2738
Epoch 70/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 1.0000 - loss: 0.0833 29/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9154 - loss: 0.2085   50/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9123 - loss: 0.2131 73/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9090 - loss: 0.2185 96/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9074 - loss: 0.2222124/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2246146/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2264167/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2275187/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2286210/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2297235/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2313267/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9035 - loss: 0.2328298/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9029 - loss: 0.2341325/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9025 - loss: 0.2349353/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9021 - loss: 0.2356382/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2361417/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9014 - loss: 0.2367453/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9012 - loss: 0.2370459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9012 - loss: 0.2371 - val_accuracy: 0.8871 - val_loss: 0.2740
Epoch 71/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 22s 48ms/step - accuracy: 1.0000 - loss: 0.0817 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9153 - loss: 0.2071   46/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9122 - loss: 0.2119 73/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2181101/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9067 - loss: 0.2223122/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2241146/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2261178/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2278208/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2293238/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9038 - loss: 0.2311271/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9032 - loss: 0.2327300/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9027 - loss: 0.2338329/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9023 - loss: 0.2347356/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9020 - loss: 0.2353387/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9017 - loss: 0.2359413/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2363437/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9013 - loss: 0.2366459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9012 - loss: 0.2368 - val_accuracy: 0.8879 - val_loss: 0.2743
Epoch 72/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 24s 53ms/step - accuracy: 1.0000 - loss: 0.0818 19/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9187 - loss: 0.2012   46/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9122 - loss: 0.2113 78/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2185111/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2227145/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2255174/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2271198/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2283228/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9043 - loss: 0.2302256/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9037 - loss: 0.2316280/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9033 - loss: 0.2327298/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9030 - loss: 0.2334316/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9027 - loss: 0.2340337/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9024 - loss: 0.2345365/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9021 - loss: 0.2352396/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9018 - loss: 0.2357431/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2362459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9013 - loss: 0.2364 - val_accuracy: 0.8893 - val_loss: 0.2732
Epoch 73/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 14s 32ms/step - accuracy: 1.0000 - loss: 0.0829 40/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9147 - loss: 0.2103   73/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9091 - loss: 0.2172105/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9070 - loss: 0.2216128/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9063 - loss: 0.2237148/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2253174/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2267201/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2280234/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2301274/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9032 - loss: 0.2321313/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9025 - loss: 0.2335340/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9021 - loss: 0.2342363/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9019 - loss: 0.2347398/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9015 - loss: 0.2353436/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9012 - loss: 0.2359459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9011 - loss: 0.2361 - val_accuracy: 0.8898 - val_loss: 0.2730
Epoch 74/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 1.0000 - loss: 0.0830 27/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9188 - loss: 0.2059   52/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9140 - loss: 0.2116 72/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9106 - loss: 0.2165 92/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2201117/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9079 - loss: 0.2223141/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9072 - loss: 0.2244170/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2261197/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2274227/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2293254/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2308281/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2320310/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9034 - loss: 0.2330338/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9030 - loss: 0.2338365/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9026 - loss: 0.2344391/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9023 - loss: 0.2348413/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9021 - loss: 0.2352436/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9019 - loss: 0.2355459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9017 - loss: 0.2357 - val_accuracy: 0.8895 - val_loss: 0.2727
Epoch 75/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 44ms/step - accuracy: 1.0000 - loss: 0.0826 28/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9192 - loss: 0.2062   58/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9133 - loss: 0.2131 90/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9095 - loss: 0.2198118/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2223142/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2244174/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9069 - loss: 0.2262206/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9063 - loss: 0.2278232/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2295259/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2309286/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9044 - loss: 0.2320306/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2327326/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9036 - loss: 0.2333350/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9033 - loss: 0.2339385/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9029 - loss: 0.2346410/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9026 - loss: 0.2350444/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9023 - loss: 0.2354459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9022 - loss: 0.2355 - val_accuracy: 0.8887 - val_loss: 0.2727
Epoch 76/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 19s 43ms/step - accuracy: 1.0000 - loss: 0.0825 31/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9187 - loss: 0.2063   60/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9129 - loss: 0.2129 87/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9098 - loss: 0.2186117/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2217153/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9074 - loss: 0.2246187/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9067 - loss: 0.2264218/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9061 - loss: 0.2281247/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2298276/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2312308/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2323342/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9036 - loss: 0.2333377/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9031 - loss: 0.2340407/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9028 - loss: 0.2345440/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9026 - loss: 0.2349459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9025 - loss: 0.2351 - val_accuracy: 0.8887 - val_loss: 0.2728
Epoch 77/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 35ms/step - accuracy: 1.0000 - loss: 0.0821 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9187 - loss: 0.2066   61/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9139 - loss: 0.2129 94/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9104 - loss: 0.2193124/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9093 - loss: 0.2220156/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2245189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2261215/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2276247/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2295286/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2313321/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2324352/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2332380/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9038 - loss: 0.2337399/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9036 - loss: 0.2341418/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9034 - loss: 0.2344443/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9032 - loss: 0.2346459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9031 - loss: 0.2348 - val_accuracy: 0.8893 - val_loss: 0.2727
Epoch 78/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 22s 49ms/step - accuracy: 1.0000 - loss: 0.0820 23/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9209 - loss: 0.2027   41/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9171 - loss: 0.2083 60/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9138 - loss: 0.2121 82/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9109 - loss: 0.2169113/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2206139/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2229165/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9076 - loss: 0.2245191/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2259226/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9063 - loss: 0.2280261/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2299289/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2311313/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2319336/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2325369/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9037 - loss: 0.2332401/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9034 - loss: 0.2338434/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9031 - loss: 0.2343459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9030 - loss: 0.2344 - val_accuracy: 0.8901 - val_loss: 0.2729
Epoch 79/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 37ms/step - accuracy: 1.0000 - loss: 0.0826 27/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9197 - loss: 0.2044   55/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9150 - loss: 0.2106 87/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9107 - loss: 0.2177121/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9091 - loss: 0.2211153/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2237189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9075 - loss: 0.2256225/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9067 - loss: 0.2277260/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2296292/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2309320/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2318354/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9043 - loss: 0.2327383/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2332409/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9037 - loss: 0.2337432/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9036 - loss: 0.2340454/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9034 - loss: 0.2342459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9034 - loss: 0.2342 - val_accuracy: 0.8906 - val_loss: 0.2725
Epoch 80/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 24s 54ms/step - accuracy: 1.0000 - loss: 0.0824 29/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9193 - loss: 0.2045   65/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9137 - loss: 0.2132 89/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9114 - loss: 0.2179107/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9105 - loss: 0.2197125/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9100 - loss: 0.2213143/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9094 - loss: 0.2229164/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2241192/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9083 - loss: 0.2255222/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9076 - loss: 0.2273252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9067 - loss: 0.2290284/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2305315/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2315341/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2322363/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2327382/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9044 - loss: 0.2331403/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2334431/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9039 - loss: 0.2338459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9037 - loss: 0.2340 - val_accuracy: 0.8901 - val_loss: 0.2723
Epoch 81/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 22s 50ms/step - accuracy: 1.0000 - loss: 0.0819 20/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9226 - loss: 0.1996   38/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9176 - loss: 0.2076 58/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9148 - loss: 0.2112 83/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9119 - loss: 0.2168111/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9103 - loss: 0.2200138/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9095 - loss: 0.2224162/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9088 - loss: 0.2239187/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2252215/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2268239/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9070 - loss: 0.2282263/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2294291/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2306319/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2315343/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2321369/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2326397/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2331423/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9042 - loss: 0.2335441/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2337459/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9040 - loss: 0.2338459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9040 - loss: 0.2338 - val_accuracy: 0.8903 - val_loss: 0.2720
Epoch 82/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 38ms/step - accuracy: 1.0000 - loss: 0.0802 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9200 - loss: 0.2026   45/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9172 - loss: 0.2074 63/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9143 - loss: 0.2117 83/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9121 - loss: 0.2159102/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9108 - loss: 0.2184130/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9099 - loss: 0.2209151/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9092 - loss: 0.2226184/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2243216/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9078 - loss: 0.2261246/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2279264/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9067 - loss: 0.2288283/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2296304/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2304329/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2312359/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2319392/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2325422/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9044 - loss: 0.2330453/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9042 - loss: 0.2332459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9041 - loss: 0.2333 - val_accuracy: 0.8906 - val_loss: 0.2720
Epoch 83/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 27s 61ms/step - accuracy: 1.0000 - loss: 0.0802 22/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9214 - loss: 0.1994   53/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9155 - loss: 0.2084 84/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9118 - loss: 0.2157113/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9102 - loss: 0.2190150/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9091 - loss: 0.2221182/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2239211/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9080 - loss: 0.2255241/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9073 - loss: 0.2273271/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2288308/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2302342/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2312370/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2318404/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2324436/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2328457/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9044 - loss: 0.2330459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9044 - loss: 0.2330 - val_accuracy: 0.8901 - val_loss: 0.2723
Epoch 84/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 20s 45ms/step - accuracy: 1.0000 - loss: 0.0799 29/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9196 - loss: 0.2027   58/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9157 - loss: 0.2097 83/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9128 - loss: 0.2154102/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9115 - loss: 0.2179121/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9108 - loss: 0.2196139/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9102 - loss: 0.2213157/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9096 - loss: 0.2225175/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9092 - loss: 0.2235193/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9088 - loss: 0.2244213/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2256239/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9078 - loss: 0.2272265/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9072 - loss: 0.2285298/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2298334/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2309361/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2315392/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2321423/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2326449/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2328459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9048 - loss: 0.2329 - val_accuracy: 0.8909 - val_loss: 0.2719
Epoch 85/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 27s 61ms/step - accuracy: 1.0000 - loss: 0.0793 18/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9236 - loss: 0.1938   36/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9174 - loss: 0.2048 56/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9148 - loss: 0.2086 82/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9118 - loss: 0.2148116/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9101 - loss: 0.2188150/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9091 - loss: 0.2218187/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2238220/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9078 - loss: 0.2257252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2275289/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9064 - loss: 0.2292327/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9057 - loss: 0.2304363/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2312397/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2318433/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2324459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9045 - loss: 0.2326 - val_accuracy: 0.8912 - val_loss: 0.2722
Epoch 86/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 17s 38ms/step - accuracy: 1.0000 - loss: 0.0791 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9200 - loss: 0.2003   49/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9170 - loss: 0.2064 72/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9138 - loss: 0.2123 96/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9119 - loss: 0.2165126/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9107 - loss: 0.2194163/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9096 - loss: 0.2222198/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2240230/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2261261/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9075 - loss: 0.2277298/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9068 - loss: 0.2292335/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2304371/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9057 - loss: 0.2312402/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2317433/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2321459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9049 - loss: 0.2323 - val_accuracy: 0.8909 - val_loss: 0.2720
Epoch 87/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 15s 33ms/step - accuracy: 1.0000 - loss: 0.0789 30/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9194 - loss: 0.2009   58/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9152 - loss: 0.2081 86/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9121 - loss: 0.2147118/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9105 - loss: 0.2183145/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9096 - loss: 0.2208176/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2226205/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2241233/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9078 - loss: 0.2260266/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2277299/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2290330/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2300364/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2308395/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2313431/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2319459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9048 - loss: 0.2321 - val_accuracy: 0.8917 - val_loss: 0.2722
Epoch 88/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 20s 45ms/step - accuracy: 1.0000 - loss: 0.0787 25/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9191 - loss: 0.1992   47/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9166 - loss: 0.2053 75/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9131 - loss: 0.2124103/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9113 - loss: 0.2167130/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9105 - loss: 0.2193155/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9098 - loss: 0.2213184/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9092 - loss: 0.2228212/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9087 - loss: 0.2244236/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2259263/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2273289/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9072 - loss: 0.2284320/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9067 - loss: 0.2295353/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9063 - loss: 0.2303388/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2310421/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2315446/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2318459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9053 - loss: 0.2319 - val_accuracy: 0.8917 - val_loss: 0.2722
Epoch 89/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 13s 30ms/step - accuracy: 1.0000 - loss: 0.0787 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9179 - loss: 0.2025   65/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9139 - loss: 0.2098 87/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9120 - loss: 0.2145110/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9110 - loss: 0.2171137/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9103 - loss: 0.2197169/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9096 - loss: 0.2218196/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9091 - loss: 0.2232221/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9086 - loss: 0.2248254/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9079 - loss: 0.2266289/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9073 - loss: 0.2282317/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9068 - loss: 0.2292351/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9064 - loss: 0.2301384/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9061 - loss: 0.2307416/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9057 - loss: 0.2313447/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2316459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9054 - loss: 0.2317 - val_accuracy: 0.8920 - val_loss: 0.2720
Epoch 90/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 13s 30ms/step - accuracy: 1.0000 - loss: 0.0794 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9179 - loss: 0.2021   68/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9138 - loss: 0.2101100/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9117 - loss: 0.2157135/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9108 - loss: 0.2192172/459 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9099 - loss: 0.2216203/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9094 - loss: 0.2233226/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2248252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9083 - loss: 0.2262283/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2277317/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2289357/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2299393/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2305428/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2311459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9056 - loss: 0.2313 - val_accuracy: 0.8909 - val_loss: 0.2717
Epoch 91/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 37ms/step - accuracy: 1.0000 - loss: 0.0784 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9173 - loss: 0.2010   58/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9142 - loss: 0.2072 85/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9114 - loss: 0.2136109/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9102 - loss: 0.2165133/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9095 - loss: 0.2189162/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9088 - loss: 0.2210189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9083 - loss: 0.2225219/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9078 - loss: 0.2242252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2261282/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2275307/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2284333/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2292366/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2300398/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2305427/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2310453/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2312459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9048 - loss: 0.2312 - val_accuracy: 0.8906 - val_loss: 0.2716
Epoch 92/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 21s 47ms/step - accuracy: 1.0000 - loss: 0.0786 27/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9179 - loss: 0.1990   57/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9140 - loss: 0.2068 89/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9107 - loss: 0.2142118/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9096 - loss: 0.2173153/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9086 - loss: 0.2204189/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9080 - loss: 0.2224227/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9073 - loss: 0.2246260/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9068 - loss: 0.2264285/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9064 - loss: 0.2275310/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2284332/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9057 - loss: 0.2291359/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2297388/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2302409/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2306427/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2308444/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2310459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9046 - loss: 0.2311 - val_accuracy: 0.8912 - val_loss: 0.2713
Epoch 93/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 37ms/step - accuracy: 1.0000 - loss: 0.0778 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9182 - loss: 0.2005   63/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9142 - loss: 0.2083 88/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9119 - loss: 0.2137111/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9107 - loss: 0.2164136/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9099 - loss: 0.2188160/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9093 - loss: 0.2205186/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9087 - loss: 0.2219215/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2236248/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9075 - loss: 0.2255278/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9070 - loss: 0.2270309/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2281338/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9061 - loss: 0.2290358/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2295384/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2299411/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2304437/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2307459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9051 - loss: 0.2309 - val_accuracy: 0.8914 - val_loss: 0.2714
Epoch 94/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 37ms/step - accuracy: 1.0000 - loss: 0.0775 28/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9176 - loss: 0.1985   54/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9141 - loss: 0.2053 79/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9111 - loss: 0.2118102/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9097 - loss: 0.2153131/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9089 - loss: 0.2181163/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2205198/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9076 - loss: 0.2224236/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9070 - loss: 0.2247270/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2264299/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9061 - loss: 0.2276334/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9057 - loss: 0.2287371/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2295399/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2300426/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2304450/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2306459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9047 - loss: 0.2306 - val_accuracy: 0.8909 - val_loss: 0.2714
Epoch 95/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 27s 61ms/step - accuracy: 1.0000 - loss: 0.0763 17/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9245 - loss: 0.1875   39/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9173 - loss: 0.2020 66/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9134 - loss: 0.2085 95/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9108 - loss: 0.2142121/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9098 - loss: 0.2168144/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9091 - loss: 0.2190171/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2206194/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9080 - loss: 0.2219226/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9074 - loss: 0.2239252/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9070 - loss: 0.2253283/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2267308/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2277339/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2286374/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2293404/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2298431/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2302458/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2304459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9049 - loss: 0.2304 - val_accuracy: 0.8920 - val_loss: 0.2712
Epoch 96/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 24s 53ms/step - accuracy: 1.0000 - loss: 0.0755 23/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9192 - loss: 0.1953   41/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9162 - loss: 0.2021 57/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9141 - loss: 0.2054 79/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9115 - loss: 0.2111101/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9100 - loss: 0.2146127/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9091 - loss: 0.2172156/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2196188/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9076 - loss: 0.2214223/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9070 - loss: 0.2235253/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2252284/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2266319/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2278354/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2287392/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2294425/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2300459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9044 - loss: 0.2302 - val_accuracy: 0.8917 - val_loss: 0.2713
Epoch 97/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 1.0000 - loss: 0.0751 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9163 - loss: 0.1995   54/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9137 - loss: 0.2046 79/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9107 - loss: 0.2111101/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9092 - loss: 0.2146124/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9085 - loss: 0.2169141/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9080 - loss: 0.2185169/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9074 - loss: 0.2203199/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9070 - loss: 0.2219234/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9064 - loss: 0.2241264/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2256294/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2269321/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2278347/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2285369/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2289393/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2293416/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9043 - loss: 0.2297437/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9042 - loss: 0.2300456/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9041 - loss: 0.2301459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9041 - loss: 0.2301 - val_accuracy: 0.8925 - val_loss: 0.2714
Epoch 98/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 26s 59ms/step - accuracy: 1.0000 - loss: 0.0739 29/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9171 - loss: 0.1977   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9143 - loss: 0.2048 84/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9112 - loss: 0.2119112/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9096 - loss: 0.2154142/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9087 - loss: 0.2183163/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2197182/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9079 - loss: 0.2208200/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9076 - loss: 0.2217230/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9070 - loss: 0.2237259/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2252293/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2267326/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9055 - loss: 0.2278358/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2285391/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2291424/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2297459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9044 - loss: 0.2299 - val_accuracy: 0.8917 - val_loss: 0.2715
Epoch 99/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 21s 47ms/step - accuracy: 1.0000 - loss: 0.0738 30/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9171 - loss: 0.1974   60/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9137 - loss: 0.2057 92/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9106 - loss: 0.2128125/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9094 - loss: 0.2163155/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9085 - loss: 0.2189176/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9081 - loss: 0.2201201/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2214229/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9072 - loss: 0.2233254/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9068 - loss: 0.2246277/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9064 - loss: 0.2257305/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9059 - loss: 0.2268329/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2275357/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2282380/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2287407/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9048 - loss: 0.2291441/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9046 - loss: 0.2296459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9045 - loss: 0.2297 - val_accuracy: 0.8920 - val_loss: 0.2718
Epoch 100/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 26s 58ms/step - accuracy: 1.0000 - loss: 0.0730 17/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9233 - loss: 0.1857   46/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9159 - loss: 0.2018 76/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9122 - loss: 0.2097104/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9103 - loss: 0.2141134/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9093 - loss: 0.2171156/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9086 - loss: 0.2189173/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9083 - loss: 0.2198190/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9079 - loss: 0.2207207/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2217230/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9072 - loss: 0.2232261/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2249287/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2260313/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2269347/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2279381/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2286415/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2292450/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9044 - loss: 0.2295459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9044 - loss: 0.2296 - val_accuracy: 0.8906 - val_loss: 0.2714
Epoch 101/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 22s 49ms/step - accuracy: 1.0000 - loss: 0.0728 28/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9173 - loss: 0.1964   59/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9141 - loss: 0.2051 86/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9113 - loss: 0.2116116/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9100 - loss: 0.2152141/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9092 - loss: 0.2176163/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9087 - loss: 0.2191185/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2204211/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9078 - loss: 0.2218235/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9072 - loss: 0.2234256/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9069 - loss: 0.2245272/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2253291/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9063 - loss: 0.2260308/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2266329/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9057 - loss: 0.2273355/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2280373/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2283393/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2287412/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2290430/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2292447/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2294459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9046 - loss: 0.2294 - val_accuracy: 0.8901 - val_loss: 0.2717
Epoch 102/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 35ms/step - accuracy: 1.0000 - loss: 0.0732 27/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9167 - loss: 0.1954   56/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9137 - loss: 0.2036 81/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9110 - loss: 0.2101106/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9097 - loss: 0.2137130/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9091 - loss: 0.2162157/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2184185/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9079 - loss: 0.2200213/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9075 - loss: 0.2216236/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9070 - loss: 0.2231263/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2245294/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9061 - loss: 0.2258325/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2268358/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2277392/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2283426/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9047 - loss: 0.2288459/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9045 - loss: 0.2291459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9045 - loss: 0.2291 - val_accuracy: 0.8901 - val_loss: 0.2719
Epoch 103/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 18s 41ms/step - accuracy: 1.0000 - loss: 0.0726 34/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9174 - loss: 0.1986   64/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9144 - loss: 0.2063 88/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9123 - loss: 0.2116111/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9111 - loss: 0.2143142/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9101 - loss: 0.2174171/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9094 - loss: 0.2192197/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9088 - loss: 0.2206225/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9082 - loss: 0.2224255/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9076 - loss: 0.2241282/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9071 - loss: 0.2253306/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9066 - loss: 0.2262325/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9063 - loss: 0.2268345/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9060 - loss: 0.2274370/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9057 - loss: 0.2279400/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2284422/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9052 - loss: 0.2288449/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2290459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9050 - loss: 0.2291 - val_accuracy: 0.8901 - val_loss: 0.2716
Epoch 104/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 22s 49ms/step - accuracy: 1.0000 - loss: 0.0723 26/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9165 - loss: 0.1951   54/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9146 - loss: 0.2031 77/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9120 - loss: 0.2093 96/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9107 - loss: 0.2127114/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9100 - loss: 0.2146132/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9096 - loss: 0.2164153/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9090 - loss: 0.2181170/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9087 - loss: 0.2191188/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9084 - loss: 0.2201205/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9081 - loss: 0.2210222/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9078 - loss: 0.2221241/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9074 - loss: 0.2233266/459 ━━━━━━━━━━━━━━━━━━━━ 0s 3ms/step - accuracy: 0.9070 - loss: 0.2245294/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9065 - loss: 0.2257322/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9061 - loss: 0.2266353/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9057 - loss: 0.2274385/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9054 - loss: 0.2281417/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9051 - loss: 0.2286449/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9049 - loss: 0.2289459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9048 - loss: 0.2290 - val_accuracy: 0.8903 - val_loss: 0.2718
Epoch 105/2000
  1/459 ━━━━━━━━━━━━━━━━━━━━ 16s 36ms/step - accuracy: 1.0000 - loss: 0.0723 32/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9163 - loss: 0.1977   57/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9143 - loss: 0.2039 81/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9117 - loss: 0.2101108/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9103 - loss: 0.2138132/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9097 - loss: 0.2163158/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9090 - loss: 0.2183183/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9085 - loss: 0.2197207/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9081 - loss: 0.2210230/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9077 - loss: 0.2225253/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9073 - loss: 0.2237281/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9068 - loss: 0.2250315/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9062 - loss: 0.2262346/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9058 - loss: 0.2271371/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9056 - loss: 0.2276401/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9053 - loss: 0.2281434/459 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9050 - loss: 0.2286459/459 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9049 - loss: 0.2288 - val_accuracy: 0.8903 - val_loss: 0.2713
  1/144 ━━━━━━━━━━━━━━━━━━━━ 10s 71ms/step 43/144 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step   83/144 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step140/144 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step144/144 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step
Neural Network
Accuracy: 0.9022474361771765
Precision: 0.9089376053962901
Recall: 0.9380438565958928
F1: 0.9232613908872902
Confusion Matrix:
[[1440  270]
 [ 178 2695]]

It doesn’t work the same way to create a graph of feature importance for the NN. I am not sure if there is a way to do this or if it even makes sense to try to.

STRETCH QUESTION|TASK 2

Join the dwellings_neighborhoods_ml.csv data to the dwelling_ml.csv on the parcel column to create a new dataset. Duplicate the code for the stretch question above and update it to use this data. Explain the differences and if this changes the model you recommend to the Client.

The additional features made a big difference in the performance of all the different types of models. I added an additional set of scores below for each model: how much better the model performed than their previous versions (the same model without the additional features). This shows that across all the models adding more features helped a lot. I would recommend the Random Forest to the Client because of the models I tested, it performed the best on the evaluation metrics explained in task 4.

df_neiborhoods = pd.read_csv("https://raw.githubusercontent.com/byuidatascience/data4dwellings/master/data-raw/dwellings_neighborhoods_ml/dwellings_neighborhoods_ml.csv")
large_df = pd.merge(df, df_neiborhoods, on="parcel")

large_X = large_df.drop(columns = ['parcel', 'yrbuilt', 'before1980'])
large_y = large_df.before1980

X_large_train, X_large_test, y_large_train, y_large_test = train_test_split(large_X, large_y, test_size=0.2, random_state=42)

# XGBoost
model_large = XGBClassifier(
    objective='binary:hinge',
    eval_metric='error',
    use_label_encoder=False
)

model_large.fit(X_large_train, y_large_train)
y_large_pred = model_large.predict(X_large_test)

accuracy_large = accuracy_score(y_large_test, y_large_pred)
precision_large = precision_score(y_large_test, y_large_pred)
recall_large = recall_score(y_large_test, y_large_pred)
f1_large = f1_score(y_large_test, y_large_pred)

print('Large Dataset XGBoost')
print('Accuracy:', accuracy_large)
print('Precision:', precision_large)
print('Recall:', recall_large)
print('F1:', f1_large)
print()
print("Difference of scores before and after adding data:")
print('Accuracy Increase:', accuracy_large - accuracy)
print('Precision Increase:', precision_large - precision)
print('Recall Increase:', recall_large - recall)
print('F1 Increase:', f1_large - f1)

Large Dataset XGBoost
Accuracy: 0.9672805292329698
Precision: 0.9676958261863923
Recall: 0.9797395079594791
F1: 0.9736804257155185

Difference of scores before and after adding data:
Accuracy Increase: 0.03950396366456488
Precision Increase: 0.031226045966612048
Recall Increase: 0.03055746827970185
F1 Increase: 0.030897366078526223

# DECISION TREE
large_tree = DecisionTreeClassifier()
large_tree.fit(X_large_train, y_large_train)
large_tree_pred = large_tree.predict(X_large_test)

large_tree_accuracy = accuracy_score(y_large_test, large_tree_pred)
large_tree_precision = precision_score(y_large_test, large_tree_pred)
large_tree_recall = recall_score(y_large_test, large_tree_pred)
large_tree_f1 = f1_score(y_large_test, large_tree_pred)

print('Large Dataset Decision Tree')
print('Accuracy:', large_tree_accuracy)
print('Precision:', large_tree_precision)
print('Recall:', large_tree_recall)
print('F1:', large_tree_f1)
print()
print("Difference of scores before and after adding data:")
print('Accuracy Increase:', large_tree_accuracy - tree_accuracy)
print('Precision Increase:', large_tree_precision - tree_precision)
print('Recall Increase:', large_tree_recall - tree_recall)
print('F1 Increase:', large_tree_f1 - tree_f1)

Large Dataset Decision Tree
Accuracy: 0.9583407831217593
Precision: 0.9626651349798966
Recall: 0.9701881331403762
F1: 0.9664119936572005

Difference of scores before and after adding data:
Accuracy Increase: 0.05892991687694149
Precision Increase: 0.035308650217316884
Recall Increase: 0.059293597811451715
F1 Increase: 0.04736019383279322

# RANDOM FOREST
large_forest = RandomForestClassifier()
large_forest.fit(X_large_train, y_large_train)
large_forest_pred = large_forest.predict(X_large_test)

large_forest_accuracy = accuracy_score(y_large_test, large_forest_pred)
large_forest_precision = precision_score(y_large_test, large_forest_pred)
large_forest_recall = recall_score(y_large_test, large_forest_pred)
large_forest_f1 = f1_score(y_large_test, large_forest_pred)

print('Large Dataset Random Forest')
print('Accuracy:', large_forest_accuracy)
print('Precision:', large_forest_precision)
print('Recall:', large_forest_recall)
print('F1:', large_forest_f1)
print()
print("Difference of scores before and after adding data:")
print('Accuracy Increase:', large_forest_accuracy - forest_accuracy)
print('Precision Increase:', large_forest_precision - forest_precision)
print('Recall Increase:', large_forest_recall - forest_recall)
print('F1 Increase:', large_forest_f1 - forest_f1)

Large Dataset Random Forest
Accuracy: 0.9688896835329877
Precision: 0.9756451145259496
Recall: 0.9739507959479016
F1: 0.9747972190034763

Difference of scores before and after adding data:
Accuracy Increase: 0.03696736190959682
Precision Increase: 0.03179762752421644
Recall Increase: 0.02616102915360985
F1 Increase: 0.028982700073292178

# NEURAL NETWORK
large_norm = MinMaxScaler().fit(X_large_train)
X_large_train = large_norm.transform(X_large_train)
X_large_test = large_norm.transform(X_large_test)

model = Sequential()
model.add(Input(shape=(len(X_large_train[0]),)))
model.add(Dense(16, activation='relu'))
model.add(Dense(8, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

opt = keras.optimizers.Adam()
model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])

early_stop = keras.callbacks.EarlyStopping(monitor='val_loss', patience=10)

history = model.fit(X_large_train, y_large_train, epochs=2000, validation_split=.2, batch_size=32, callbacks=[early_stop],shuffle=False)

hist = pd.DataFrame(history.history)

hist = hist.reset_index()

predictions = model.predict(X_large_test)
binary_predictions = (predictions >= 0.5).astype(int)

large_nn_accuracy = accuracy_score(y_large_test, binary_predictions)
large_nn_precision = precision_score(y_large_test, binary_predictions)
large_nn_recall = recall_score(y_large_test, binary_predictions)
large_nn_f1 = f1_score(y_large_test, binary_predictions)

print('Large Dataset Neural Network')
print('Accuracy:', large_nn_accuracy)
print('Precision:', large_nn_precision)
print('Recall:', large_nn_recall)
print('F1:', large_nn_f1)
print()
print("Difference of scores before and after adding data:")
print('Accuracy Increase:', large_nn_accuracy - nn_accuracy)
print('Precision Increase:', large_nn_precision - nn_precision)
print('Recall Increase:', large_nn_recall - nn_recall)
print('F1 Increase:', large_nn_f1 - nn_f1)

Epoch 1/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 11:36 1s/step - accuracy: 0.3750 - loss: 0.7101 29/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.5416 - loss: 0.6891   60/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6022 - loss: 0.6679 88/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6420 - loss: 0.6465116/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6729 - loss: 0.6231143/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.6956 - loss: 0.6015175/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7163 - loss: 0.5783204/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7315 - loss: 0.5588232/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7438 - loss: 0.5417264/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7557 - loss: 0.5240297/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7662 - loss: 0.5075326/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7741 - loss: 0.4946353/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7808 - loss: 0.4835376/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7859 - loss: 0.4748407/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7923 - loss: 0.4638437/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.7977 - loss: 0.4541467/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8027 - loss: 0.4451497/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8073 - loss: 0.4366527/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.8116 - loss: 0.4286560/560 ━━━━━━━━━━━━━━━━━━━━ 3s 3ms/step - accuracy: 0.8161 - loss: 0.4202 - val_accuracy: 0.9350 - val_loss: 0.1669
Epoch 2/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 21s 38ms/step - accuracy: 0.9375 - loss: 0.1516 24/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9270 - loss: 0.1761   46/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9291 - loss: 0.1739 71/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9309 - loss: 0.1709 90/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9323 - loss: 0.1695116/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9340 - loss: 0.1669148/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9352 - loss: 0.1645180/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9358 - loss: 0.1631214/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9365 - loss: 0.1614246/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9370 - loss: 0.1602277/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9374 - loss: 0.1591306/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9377 - loss: 0.1584339/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9380 - loss: 0.1576372/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9383 - loss: 0.1570400/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9385 - loss: 0.1566430/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9386 - loss: 0.1563464/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9388 - loss: 0.1560496/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9389 - loss: 0.1557528/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9390 - loss: 0.1554553/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9392 - loss: 0.1551560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9392 - loss: 0.1550 - val_accuracy: 0.9452 - val_loss: 0.1435
Epoch 3/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 23s 41ms/step - accuracy: 0.9375 - loss: 0.1100 27/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9331 - loss: 0.1519   54/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9373 - loss: 0.1480 83/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9398 - loss: 0.1463109/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9420 - loss: 0.1442127/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9431 - loss: 0.1429150/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9441 - loss: 0.1416175/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9447 - loss: 0.1408199/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9453 - loss: 0.1398219/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9457 - loss: 0.1391237/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9461 - loss: 0.1386257/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9465 - loss: 0.1380279/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9469 - loss: 0.1374302/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9471 - loss: 0.1370329/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9474 - loss: 0.1366355/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9476 - loss: 0.1363379/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9477 - loss: 0.1361402/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9478 - loss: 0.1359427/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9478 - loss: 0.1359449/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9478 - loss: 0.1358475/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9478 - loss: 0.1358499/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9478 - loss: 0.1358522/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9478 - loss: 0.1357549/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9479 - loss: 0.1356560/560 ━━━━━━━━━━━━━━━━━━━━ 2s 3ms/step - accuracy: 0.9479 - loss: 0.1356 - val_accuracy: 0.9490 - val_loss: 0.1376
Epoch 4/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 33s 59ms/step - accuracy: 1.0000 - loss: 0.0950 28/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9480 - loss: 0.1430   56/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9483 - loss: 0.1389 86/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9488 - loss: 0.1375108/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9497 - loss: 0.1357130/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9503 - loss: 0.1343151/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9507 - loss: 0.1333171/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9509 - loss: 0.1327189/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9511 - loss: 0.1321212/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9515 - loss: 0.1313236/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9518 - loss: 0.1306266/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9521 - loss: 0.1298298/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9524 - loss: 0.1291326/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9525 - loss: 0.1287353/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9526 - loss: 0.1284382/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9526 - loss: 0.1282413/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9526 - loss: 0.1280441/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9525 - loss: 0.1280471/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9525 - loss: 0.1280498/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9525 - loss: 0.1280519/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9525 - loss: 0.1279549/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9524 - loss: 0.1279560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9524 - loss: 0.1279 - val_accuracy: 0.9506 - val_loss: 0.1345
Epoch 5/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 26s 47ms/step - accuracy: 1.0000 - loss: 0.0875 25/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9488 - loss: 0.1370   47/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9494 - loss: 0.1343 74/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9504 - loss: 0.1323100/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9516 - loss: 0.1308124/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9526 - loss: 0.1293144/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9531 - loss: 0.1283166/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9534 - loss: 0.1276194/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9539 - loss: 0.1268225/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9544 - loss: 0.1258256/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9547 - loss: 0.1250287/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9550 - loss: 0.1242315/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9552 - loss: 0.1238339/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9553 - loss: 0.1234366/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9553 - loss: 0.1232398/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9553 - loss: 0.1229432/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9552 - loss: 0.1229468/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9551 - loss: 0.1229499/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9551 - loss: 0.1229527/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9550 - loss: 0.1228555/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9550 - loss: 0.1228560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9550 - loss: 0.1228 - val_accuracy: 0.9513 - val_loss: 0.1319
Epoch 6/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 26s 47ms/step - accuracy: 1.0000 - loss: 0.0813 24/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9513 - loss: 0.1317   46/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9519 - loss: 0.1297 73/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9528 - loss: 0.1276 99/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9538 - loss: 0.1262129/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9546 - loss: 0.1244162/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9552 - loss: 0.1231195/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9555 - loss: 0.1222229/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9559 - loss: 0.1212263/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9562 - loss: 0.1203297/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9564 - loss: 0.1196327/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9565 - loss: 0.1191349/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9565 - loss: 0.1188380/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9565 - loss: 0.1185416/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9564 - loss: 0.1184451/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9563 - loss: 0.1184483/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9563 - loss: 0.1184519/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9562 - loss: 0.1183551/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9561 - loss: 0.1183560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9561 - loss: 0.1183 - val_accuracy: 0.9531 - val_loss: 0.1294
Epoch 7/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 24s 45ms/step - accuracy: 1.0000 - loss: 0.0751 26/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9504 - loss: 0.1279   47/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9519 - loss: 0.1249 69/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9530 - loss: 0.1233 91/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9540 - loss: 0.1225112/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9549 - loss: 0.1210137/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9557 - loss: 0.1197163/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9561 - loss: 0.1189193/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9564 - loss: 0.1180227/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9568 - loss: 0.1170258/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9571 - loss: 0.1163287/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9573 - loss: 0.1156317/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9575 - loss: 0.1151349/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9576 - loss: 0.1147385/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9576 - loss: 0.1143422/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9576 - loss: 0.1142461/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9575 - loss: 0.1142497/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9574 - loss: 0.1142528/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9574 - loss: 0.1142559/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9573 - loss: 0.1142560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9573 - loss: 0.1142 - val_accuracy: 0.9537 - val_loss: 0.1274
Epoch 8/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 23s 42ms/step - accuracy: 1.0000 - loss: 0.0703 32/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9525 - loss: 0.1239   65/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9545 - loss: 0.1197101/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9558 - loss: 0.1179134/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9568 - loss: 0.1162170/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9573 - loss: 0.1151205/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9577 - loss: 0.1141241/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9581 - loss: 0.1131279/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9585 - loss: 0.1122309/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9587 - loss: 0.1116335/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9588 - loss: 0.1112363/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9589 - loss: 0.1109395/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9590 - loss: 0.1107427/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9590 - loss: 0.1106460/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9589 - loss: 0.1106487/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9589 - loss: 0.1106519/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9588 - loss: 0.1106552/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9588 - loss: 0.1106560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9588 - loss: 0.1106 - val_accuracy: 0.9549 - val_loss: 0.1254
Epoch 9/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 35s 64ms/step - accuracy: 1.0000 - loss: 0.0669 24/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9541 - loss: 0.1188   53/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9562 - loss: 0.1165 78/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9573 - loss: 0.1158105/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9581 - loss: 0.1142136/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9588 - loss: 0.1128166/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9591 - loss: 0.1119196/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9594 - loss: 0.1111229/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9597 - loss: 0.1101258/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9599 - loss: 0.1095286/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9601 - loss: 0.1088311/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9603 - loss: 0.1084335/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9604 - loss: 0.1080362/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9604 - loss: 0.1077394/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9605 - loss: 0.1075425/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9604 - loss: 0.1074455/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9603 - loss: 0.1074483/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9603 - loss: 0.1074516/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9602 - loss: 0.1074554/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9601 - loss: 0.1074560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9601 - loss: 0.1074 - val_accuracy: 0.9555 - val_loss: 0.1238
Epoch 10/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 19s 35ms/step - accuracy: 1.0000 - loss: 0.0625 29/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9560 - loss: 0.1156   60/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9579 - loss: 0.1125 90/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9586 - loss: 0.1117115/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9593 - loss: 0.1103148/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9598 - loss: 0.1090182/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9600 - loss: 0.1082215/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9603 - loss: 0.1073235/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9605 - loss: 0.1068266/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9607 - loss: 0.1061301/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9609 - loss: 0.1054339/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9610 - loss: 0.1049380/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9611 - loss: 0.1045419/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9610 - loss: 0.1044457/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9609 - loss: 0.1044495/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9608 - loss: 0.1044531/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9608 - loss: 0.1045560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9607 - loss: 0.1045 - val_accuracy: 0.9564 - val_loss: 0.1226
Epoch 11/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 39s 70ms/step - accuracy: 1.0000 - loss: 0.0595 24/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9590 - loss: 0.1103   44/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9591 - loss: 0.1100 65/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9593 - loss: 0.1091 86/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9596 - loss: 0.1088111/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9602 - loss: 0.1074135/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9605 - loss: 0.1065163/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9607 - loss: 0.1058189/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9609 - loss: 0.1052223/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9613 - loss: 0.1043249/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9615 - loss: 0.1038279/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9617 - loss: 0.1031311/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9619 - loss: 0.1026346/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9620 - loss: 0.1022378/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9621 - loss: 0.1019413/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9621 - loss: 0.1017446/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9620 - loss: 0.1018479/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9619 - loss: 0.1018513/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9619 - loss: 0.1018541/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9618 - loss: 0.1019560/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9617 - loss: 0.1019560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9617 - loss: 0.1019 - val_accuracy: 0.9571 - val_loss: 0.1215
Epoch 12/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 16s 30ms/step - accuracy: 1.0000 - loss: 0.0561 36/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9587 - loss: 0.1079   74/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9595 - loss: 0.1061113/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9605 - loss: 0.1047150/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9610 - loss: 0.1035183/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9613 - loss: 0.1029218/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9617 - loss: 0.1020252/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9619 - loss: 0.1013283/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9621 - loss: 0.1007317/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9623 - loss: 0.1002356/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9623 - loss: 0.0998396/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9624 - loss: 0.0995434/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9623 - loss: 0.0995470/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9623 - loss: 0.0996498/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9622 - loss: 0.0996527/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9621 - loss: 0.0996553/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9621 - loss: 0.0997560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9621 - loss: 0.0997 - val_accuracy: 0.9564 - val_loss: 0.1210
Epoch 13/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 25s 46ms/step - accuracy: 1.0000 - loss: 0.0544 26/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9575 - loss: 0.1046   51/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9586 - loss: 0.1037 79/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9595 - loss: 0.1037108/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9607 - loss: 0.1026130/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9612 - loss: 0.1019155/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9616 - loss: 0.1013187/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9619 - loss: 0.1008220/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9624 - loss: 0.1000253/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9627 - loss: 0.0994285/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9629 - loss: 0.0987309/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9630 - loss: 0.0984332/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9631 - loss: 0.0981352/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9631 - loss: 0.0979379/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9632 - loss: 0.0977416/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9632 - loss: 0.0976448/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9631 - loss: 0.0977484/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9631 - loss: 0.0977514/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9630 - loss: 0.0978549/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9629 - loss: 0.0978560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9629 - loss: 0.0979 - val_accuracy: 0.9571 - val_loss: 0.1203
Epoch 14/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 17s 31ms/step - accuracy: 1.0000 - loss: 0.0506 31/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9574 - loss: 0.1029   58/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9584 - loss: 0.1016 92/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9596 - loss: 0.1013126/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9607 - loss: 0.1000151/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9612 - loss: 0.0995181/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9615 - loss: 0.0991211/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9620 - loss: 0.0984245/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9624 - loss: 0.0977281/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9628 - loss: 0.0970316/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9630 - loss: 0.0965347/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9632 - loss: 0.0962378/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0959410/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9634 - loss: 0.0958442/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9634 - loss: 0.0959466/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0960493/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0960515/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0960538/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0961560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9632 - loss: 0.0961 - val_accuracy: 0.9573 - val_loss: 0.1195
Epoch 15/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 19s 36ms/step - accuracy: 1.0000 - loss: 0.0469 25/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9628 - loss: 0.0988   42/560 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9624 - loss: 0.0994 67/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9626 - loss: 0.0992 95/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9630 - loss: 0.0989123/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9635 - loss: 0.0981152/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9637 - loss: 0.0975189/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9638 - loss: 0.0970225/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9642 - loss: 0.0962263/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9644 - loss: 0.0956301/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9646 - loss: 0.0950334/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9648 - loss: 0.0946372/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0943407/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9650 - loss: 0.0942445/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0943481/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9648 - loss: 0.0944519/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0944555/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0945560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9646 - loss: 0.0945 - val_accuracy: 0.9571 - val_loss: 0.1189
Epoch 16/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 19s 35ms/step - accuracy: 1.0000 - loss: 0.0450 38/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9616 - loss: 0.0977   72/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9620 - loss: 0.0974104/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9628 - loss: 0.0968133/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0962169/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9635 - loss: 0.0957200/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9639 - loss: 0.0952235/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9642 - loss: 0.0945273/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9645 - loss: 0.0939302/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9646 - loss: 0.0934329/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0931355/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9648 - loss: 0.0929383/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0927414/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0927446/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0928472/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9648 - loss: 0.0928493/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9648 - loss: 0.0929524/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0929554/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0930560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9647 - loss: 0.0930 - val_accuracy: 0.9580 - val_loss: 0.1185
Epoch 17/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 24s 44ms/step - accuracy: 1.0000 - loss: 0.0445 25/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9624 - loss: 0.0950   49/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9622 - loss: 0.0955 76/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9625 - loss: 0.0960106/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0954132/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9636 - loss: 0.0948156/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9639 - loss: 0.0944187/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9641 - loss: 0.0941220/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9645 - loss: 0.0934255/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0929284/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0923304/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9650 - loss: 0.0921330/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9651 - loss: 0.0918358/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9652 - loss: 0.0916386/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9653 - loss: 0.0914414/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9654 - loss: 0.0913441/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9653 - loss: 0.0914469/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9653 - loss: 0.0915503/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9652 - loss: 0.0915538/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9651 - loss: 0.0916560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9651 - loss: 0.0917 - val_accuracy: 0.9584 - val_loss: 0.1178
Epoch 18/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 18s 32ms/step - accuracy: 1.0000 - loss: 0.0437 33/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9608 - loss: 0.0949   63/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9618 - loss: 0.0945 96/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9626 - loss: 0.0945127/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0938164/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9638 - loss: 0.0933200/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9642 - loss: 0.0927228/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9646 - loss: 0.0922261/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0916296/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9652 - loss: 0.0911326/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9653 - loss: 0.0907346/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9654 - loss: 0.0905370/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9655 - loss: 0.0904401/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9657 - loss: 0.0902432/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9657 - loss: 0.0902467/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9656 - loss: 0.0903502/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9656 - loss: 0.0904533/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9655 - loss: 0.0905560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9655 - loss: 0.0905 - val_accuracy: 0.9580 - val_loss: 0.1180
Epoch 19/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 18s 33ms/step - accuracy: 1.0000 - loss: 0.0433 31/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9607 - loss: 0.0940   63/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9618 - loss: 0.0934 92/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9625 - loss: 0.0935117/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9631 - loss: 0.0929140/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9636 - loss: 0.0924174/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9640 - loss: 0.0921204/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9644 - loss: 0.0915239/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9648 - loss: 0.0909274/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9652 - loss: 0.0903313/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9655 - loss: 0.0898350/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9657 - loss: 0.0894381/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9659 - loss: 0.0892408/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9660 - loss: 0.0891438/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9660 - loss: 0.0892465/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9659 - loss: 0.0892503/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9659 - loss: 0.0893539/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9659 - loss: 0.0894560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9658 - loss: 0.0894 - val_accuracy: 0.9584 - val_loss: 0.1177
Epoch 20/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 17s 31ms/step - accuracy: 1.0000 - loss: 0.0434 34/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9595 - loss: 0.0932   71/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9609 - loss: 0.0928105/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9621 - loss: 0.0923143/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9630 - loss: 0.0916174/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9635 - loss: 0.0913207/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9641 - loss: 0.0907242/560 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step - accuracy: 0.9646 - loss: 0.0901268/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0896286/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9651 - loss: 0.0893306/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9652 - loss: 0.0890333/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9654 - loss: 0.0888356/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9656 - loss: 0.0886384/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9657 - loss: 0.0884413/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9658 - loss: 0.0883444/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9658 - loss: 0.0884470/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9658 - loss: 0.0884494/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9658 - loss: 0.0885520/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9658 - loss: 0.0885552/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9658 - loss: 0.0886560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9658 - loss: 0.0886 - val_accuracy: 0.9578 - val_loss: 0.1176
Epoch 21/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 37s 68ms/step - accuracy: 1.0000 - loss: 0.0422 16/560 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9637 - loss: 0.0856   37/560 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9593 - loss: 0.0927 64/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9607 - loss: 0.0923 87/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9615 - loss: 0.0925111/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9626 - loss: 0.0917143/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9634 - loss: 0.0911172/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9639 - loss: 0.0908201/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9645 - loss: 0.0902230/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9650 - loss: 0.0896259/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9653 - loss: 0.0892292/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9658 - loss: 0.0886327/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9660 - loss: 0.0882360/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9663 - loss: 0.0879392/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0877421/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0876446/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0877476/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0877496/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0878522/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0878557/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0878560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9665 - loss: 0.0878 - val_accuracy: 0.9573 - val_loss: 0.1179
Epoch 22/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 31s 57ms/step - accuracy: 1.0000 - loss: 0.0406 26/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9594 - loss: 0.0913   52/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9602 - loss: 0.0911 82/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9611 - loss: 0.0916110/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9623 - loss: 0.0908141/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9632 - loss: 0.0902170/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9638 - loss: 0.0898196/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9643 - loss: 0.0894227/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9648 - loss: 0.0887258/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9652 - loss: 0.0882290/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9656 - loss: 0.0876328/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9659 - loss: 0.0872357/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9661 - loss: 0.0869383/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9662 - loss: 0.0867409/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9663 - loss: 0.0866436/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0867460/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0867487/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0868520/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0868557/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0869560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9664 - loss: 0.0869 - val_accuracy: 0.9582 - val_loss: 0.1176
Epoch 23/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 18s 33ms/step - accuracy: 1.0000 - loss: 0.0397 32/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9590 - loss: 0.0911   62/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9604 - loss: 0.0906 91/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9615 - loss: 0.0906117/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9626 - loss: 0.0899144/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9634 - loss: 0.0894164/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9638 - loss: 0.0891186/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9642 - loss: 0.0889214/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0883240/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9650 - loss: 0.0878264/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9653 - loss: 0.0873290/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9657 - loss: 0.0869318/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9659 - loss: 0.0866352/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9662 - loss: 0.0862386/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0860413/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0859444/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0860475/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0860500/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0860525/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0861554/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0861560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9665 - loss: 0.0861 - val_accuracy: 0.9582 - val_loss: 0.1187
Epoch 24/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 24s 43ms/step - accuracy: 1.0000 - loss: 0.0394 20/560 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9615 - loss: 0.0863   42/560 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9597 - loss: 0.0897 66/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9607 - loss: 0.0898 91/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9617 - loss: 0.0898114/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9627 - loss: 0.0892136/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0887164/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9640 - loss: 0.0883202/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0877231/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9652 - loss: 0.0871261/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9656 - loss: 0.0865290/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9659 - loss: 0.0860320/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9662 - loss: 0.0857349/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0854377/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9666 - loss: 0.0852407/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0850441/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0851475/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0852508/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0852539/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0852560/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0853560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9668 - loss: 0.0853 - val_accuracy: 0.9582 - val_loss: 0.1190
Epoch 25/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 30s 54ms/step - accuracy: 1.0000 - loss: 0.0395 25/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9596 - loss: 0.0885   55/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9599 - loss: 0.0888 86/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9609 - loss: 0.0892117/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9623 - loss: 0.0884150/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9633 - loss: 0.0877186/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9640 - loss: 0.0873222/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9647 - loss: 0.0865261/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9652 - loss: 0.0858296/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9657 - loss: 0.0852332/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9660 - loss: 0.0848367/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9663 - loss: 0.0845402/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0843432/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9666 - loss: 0.0844467/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9666 - loss: 0.0844499/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9666 - loss: 0.0845534/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9666 - loss: 0.0845560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9666 - loss: 0.0845 - val_accuracy: 0.9591 - val_loss: 0.1190
Epoch 26/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 18s 32ms/step - accuracy: 1.0000 - loss: 0.0393 32/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9591 - loss: 0.0888   59/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9604 - loss: 0.0882 88/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9614 - loss: 0.0883120/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9628 - loss: 0.0874143/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9634 - loss: 0.0870167/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9640 - loss: 0.0867195/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9645 - loss: 0.0863221/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9650 - loss: 0.0857245/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9653 - loss: 0.0853276/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9657 - loss: 0.0847302/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9660 - loss: 0.0843327/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9663 - loss: 0.0841357/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0838387/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9667 - loss: 0.0836419/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0835445/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0836473/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0836505/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0837535/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9669 - loss: 0.0837560/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9669 - loss: 0.0837560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9669 - loss: 0.0837 - val_accuracy: 0.9593 - val_loss: 0.1197
Epoch 27/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 19s 35ms/step - accuracy: 1.0000 - loss: 0.0380 31/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9591 - loss: 0.0889   57/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9604 - loss: 0.0880 86/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9614 - loss: 0.0881110/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9626 - loss: 0.0874136/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9635 - loss: 0.0868165/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9641 - loss: 0.0863184/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9645 - loss: 0.0861208/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9649 - loss: 0.0855233/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9654 - loss: 0.0850265/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9658 - loss: 0.0844294/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9661 - loss: 0.0839325/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9665 - loss: 0.0835363/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9668 - loss: 0.0832402/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9670 - loss: 0.0829440/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9670 - loss: 0.0830474/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9670 - loss: 0.0831511/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9671 - loss: 0.0831548/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9671 - loss: 0.0831560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9671 - loss: 0.0831 - val_accuracy: 0.9593 - val_loss: 0.1193
Epoch 28/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 29s 53ms/step - accuracy: 1.0000 - loss: 0.0381 24/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9643 - loss: 0.0874   48/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9641 - loss: 0.0874 77/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9643 - loss: 0.0874105/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9650 - loss: 0.0866131/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9656 - loss: 0.0860152/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9659 - loss: 0.0855170/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9661 - loss: 0.0854189/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0851212/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9667 - loss: 0.0845233/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9669 - loss: 0.0840256/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9671 - loss: 0.0836278/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9673 - loss: 0.0832305/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9676 - loss: 0.0828333/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9677 - loss: 0.0825361/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9679 - loss: 0.0823391/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9680 - loss: 0.0820418/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9680 - loss: 0.0820443/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9680 - loss: 0.0821469/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9680 - loss: 0.0821495/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9680 - loss: 0.0821522/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9679 - loss: 0.0821549/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9679 - loss: 0.0821560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step - accuracy: 0.9679 - loss: 0.0822 - val_accuracy: 0.9586 - val_loss: 0.1205
Epoch 29/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 18s 34ms/step - accuracy: 1.0000 - loss: 0.0368 35/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9636 - loss: 0.0880   62/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9640 - loss: 0.0872 91/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9645 - loss: 0.0869123/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9655 - loss: 0.0859153/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9660 - loss: 0.0852187/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9664 - loss: 0.0847218/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9669 - loss: 0.0840251/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9672 - loss: 0.0833285/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9676 - loss: 0.0827322/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9679 - loss: 0.0822352/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9681 - loss: 0.0819381/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9682 - loss: 0.0816418/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9683 - loss: 0.0815457/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9683 - loss: 0.0815494/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9683 - loss: 0.0816532/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9683 - loss: 0.0816560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9683 - loss: 0.0816 - val_accuracy: 0.9586 - val_loss: 0.1211
Epoch 30/2000
  1/560 ━━━━━━━━━━━━━━━━━━━━ 19s 34ms/step - accuracy: 1.0000 - loss: 0.0367 34/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9636 - loss: 0.0871   66/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9643 - loss: 0.0863 92/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9648 - loss: 0.0861123/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9657 - loss: 0.0851154/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9663 - loss: 0.0844188/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9667 - loss: 0.0839222/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9672 - loss: 0.0831254/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9676 - loss: 0.0825290/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9680 - loss: 0.0818328/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9683 - loss: 0.0813361/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9685 - loss: 0.0810392/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9686 - loss: 0.0808419/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9686 - loss: 0.0807450/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9686 - loss: 0.0808485/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9686 - loss: 0.0808518/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9686 - loss: 0.0808548/560 ━━━━━━━━━━━━━━━━━━━━ 0s 2ms/step - accuracy: 0.9686 - loss: 0.0808560/560 ━━━━━━━━━━━━━━━━━━━━ 1s 2ms/step - accuracy: 0.9686 - loss: 0.0808 - val_accuracy: 0.9580 - val_loss: 0.1219
  1/175 ━━━━━━━━━━━━━━━━━━━━ 14s 85ms/step 47/175 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step  102/175 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step162/175 ━━━━━━━━━━━━━━━━━━━━ 0s 946us/step175/175 ━━━━━━━━━━━━━━━━━━━━ 0s 1ms/step  
Large Dataset Neural Network
Accuracy: 0.9551224745217236
Precision: 0.9569309754706218
Recall: 0.9710564399421129
F1: 0.9639419623617297

Difference of scores before and after adding data:
Accuracy Increase: 0.0528750383445471
Precision Increase: 0.04799337007433169
Recall Increase: 0.03301258334622004
F1 Increase: 0.040680571474439486

STRETCH QUESTION|TASK 3

Can you build a model that predicts the year a house was built? Explain the model and the evaluation metrics you would use to determine if the model is good.

I decided to use the XGBRegressor for this problem because it is fairly easy to build and the XGBoost seemed to perform about as well as the Random Forest in the classification problem, so I figured it would do fairly well on the regression problem as well. I decided to do some hyperparameter tuning with a Grid Search (I commented out the GridSearchCV code because it takes a long time to run and I only needed to run it once). After that I got an MSE of 12.6 (ish) which suggests that the model was predicting within 12.6 years of the actual value (so if it guessed a certain home was built in 1983, the actual value could be +-12.6 years of that). It performed with an MAE of 6.9 (ish), which means that on average the model predicted 6.9 years off of the actual value. Lastly the R^2 value is difficult to explain, but put simply it is a measure of how well the model explains the variance in the yrbuilt values. So 88.5% of the variation in the model is explained by the model while the remaining 11.5% variance is due to unexplained factors (a higher R^2 score is better, with 1 being the best).

from sklearn.model_selection import GridSearchCV
from sklearn.metrics import mean_squared_error, mean_absolute_error, r2_score

X_reg = large_df.drop(columns = ['parcel', 'yrbuilt', 'before1980'])
y_reg = large_df.yrbuilt

X_reg_train, X_reg_test, y_reg_train, y_reg_test = train_test_split(X_reg, y_reg, test_size=0.2, random_state=42)

# param_grid = {
#     'n_estimators': [100, 300, 500],
#     'learning_rate': [0.01, 0.1, 0.2],
#     'max_depth': [3, 5, 7],
#     'subsample': [0.7, 0.8, 1.0],
#     'colsample_bytree': [0.7, 0.8, 1.0]
# }
# search = GridSearchCV(XGBRegressor(), param_grid, cv=5, scoring='neg_mean_squared_error', n_jobs=-1)
# search.fit(X_reg_train, y_reg_train)
# best_model = search.best_estimator_
# print("Best parameters:", search.best_params_)

regr = XGBRegressor(colsample_bytree=0.7,learning_rate=0.2,max_depth=7,n_estimators=500,subsample=0.8)
regr.fit(X_reg_train, y_reg_train)
reg_pred = regr.predict(X_reg_test)

rmse = np.sqrt(mean_squared_error(y_reg_test, reg_pred))
mae = mean_absolute_error(y_reg_test, reg_pred)
r2 = r2_score(y_reg_test, reg_pred)

print(f"RMSE: {rmse}")
print(f"MAE: {mae}")
print(f"R^2: {r2}")

RMSE: 12.637653317450606
MAE: 6.895981788635254
R^2: 0.8850180506706238

---